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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10769
    Prev
    Next
    INDEX
    Explanations

    instances of the word "commit" or "commitment"

    oai_token-act-pair · gemini-2.0-flash

    commitment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     commitment
    -0.75
     COMMIT
    -0.73
    tvguidetime
    -0.72
     commit
    -0.71
    Commitment
    -0.70
     Commitment
    -0.69
     Commit
    -0.69
     commitments
    -0.67
    !*\
    -0.65
    commitment
    -0.64
    POSITIVE LOGITS
     cref
    0.68
    +#+#
    0.56
    Geplaatst
    0.56
    ghalaya
    0.56
     st
    0.54
    routeProvider
    0.53
    tan
    0.53
    MethodManager
    0.53
    ⋱
    0.52
    FlatAppearance
    0.50
    Activations Density 0.865%

    No Known Activations