© 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
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 608
    Prev
    Next
    INDEX
    Explanations

    to be

    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
    localctx
    -0.56
    findpost
    -0.51
    Autoritní
    -0.51
    iastical
    -0.50
    LikeLiked
    -0.50
    MMdd
    -0.49
    duate
    -0.49
    DispatchToProps
    -0.48
    tiary
    -0.47
    ObjectMeta
    -0.46
    POSITIVE LOGITS
     smelled
    0.58
     looked
    0.56
    .}\
    0.53
    resz
    0.52
     allowed
    0.51
     endroits
    0.51
     flowed
    0.50
     préféré
    0.50
    Hochspringen
    0.49
    posób
    0.49
    Activations Density 0.002%

    No Known Activations