© 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. 6665
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical activities and personal achievements

    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
    266
    +0.09
    0.3%
    576
    +0.09
    0.2%
    227
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.09
    0.10
    1372
    +0.09
    0.07
    1013
    +0.08
    0.09
    Negative Logits
     aen
    -1.16
     §.
    -1.15
     lyon
    -1.12
     fta
    -1.11
     claudia
    -1.09
     mef
    -1.08
     ftu
    -1.07
     fei
    -1.07
     effe
    -1.05
     yves
    -1.05
    POSITIVE LOGITS
     since
    1.28
     lately
    1.27
    since
    1.10
     recently
    0.95
    Since
    0.90
     SINCE
    0.89
     Since
    0.88
     recent
    0.86
     sejak
    0.84
     depuis
    0.81
    Activations Density 0.996%

    No Known Activations