© 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. Gemma-2-2B
    5. 4-CLT-HP
    7. 3264
    Prev
    Next
    INDEX
    Explanations

    not

    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
     Paglinawan
    -0.74
    SourceChecksum
    -0.71
     mergeFrom
    -0.69
    oa̍t
    -0.68
    msgTypes
    -0.65
    localctx
    -0.61
    Хьажоргаш
    -0.59
     curiosa
    -0.59
     للاسماء
    -0.58
     elettrica
    -0.57
    POSITIVE LOGITS
     even
    0.96
    even
    0.83
     incluso
    0.70
    Incluso
    0.66
    Even
    0.65
     Even
    0.63
     jopa
    0.63
     EVEN
    0.62
    EVEN
    0.62
     даже
    0.62
    Activations Density 0.007%

    No Known Activations