© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 6802
    Prev
    Next
    INDEX
    Explanations

    phrases related to construction and facilities management

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.25
    0.9%
    394
    +0.19
    0.7%
    1224
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    394
    +0.25
    0.14
    1224
    +0.19
    0.14
    227
    +0.15
    0.15
    Negative Logits
    <bos>
    -1.18
    __;
    -0.60
     kaarangay
    -0.58
    fizierung
    -0.55
     >=",
    -0.54
     gynhyrchwyd
    -0.52
    ัติ
    -0.52
    󠁿
    -0.52
    )_/¯
    -0.52
     Baillargeon
    -0.52
    POSITIVE LOGITS
     inev
    1.80
     reluct
    1.78
     indestru
    1.78
     maneu
    1.74
     disagre
    1.71
     apprehen
    1.68
     depic
    1.66
     shenan
    1.66
     impra
    1.64
     emphat
    1.63
    Activations Density 2.514%

    No Known Activations