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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 14123
    Prev
    Next
    INDEX
    Explanations

    phrases related to feasibility or possibility

    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
    1671
    +0.19
    0.7%
    168
    +0.19
    0.7%
    1339
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    168
    +0.19
    0.04
    1671
    +0.19
    0.04
    1339
    +0.14
    0.03
    Negative Logits
    ритори
    -0.47
    Mehr
    -0.46
    visiae
    -0.46
    getCell
    -0.44
     akong
    -0.43
    обходи
    -0.43
    circuit
    -0.42
    hed
    -0.42
    Circuit
    -0.42
    quisa
    -0.41
    POSITIVE LOGITS
     fei
    0.95
     fta
    0.94
     poff
    0.94
     wien
    0.91
     fep
    0.90
     POSSIBLE
    0.88
     Possible
    0.88
    possible
    0.88
     ftu
    0.87
     fup
    0.85
    Activations Density 0.080%

    No Known Activations