© 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. 4-CLT-HP
    7. 71
    Prev
    Next
    INDEX
    Explanations

    promises and commitments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ConstraintMaker
    -0.75
    culable
    -0.57
    ierungs
    -0.54
     its
    -0.54
    RTLE
    -0.52
     себе
    -0.52
    onaceous
    -0.52
     itself
    -0.52
    ')['
    -0.52
    <bos>
    -0.51
    POSITIVE LOGITS
     suivante
    0.59
     of
    0.58
    apimachinery
    0.52
    ellschaft
    0.51
    InjectAttribute
    0.51
     propOrder
    0.50
     ragazzo
    0.49
    FieldNumber
    0.48
     EventArgs
    0.48
    newswire
    0.47
    Activations Density 0.005%

    No Known Activations