© 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. 5-CLT-HP
    7. 2109
    Prev
    Next
    INDEX
    Explanations

    enters

    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
    .
    -0.77
    hasMoreElements
    -0.61
    .”
    -0.55
    UnitTesting
    -0.55
    harusnya
    -0.55
     sauver
    -0.55
    ().
    -0.55
    pisah
    -0.54
     manguera
    -0.54
     preuves
    -0.53
    POSITIVE LOGITS
     myſelf
    0.62
    ſelf
    0.61
     himſelf
    0.57
     ſeveral
    0.56
    <bos>
    0.56
     themſelves
    0.52
     theſe
    0.52
     juſ
    0.51
     ourselves
    0.51
    ſelves
    0.51
    Activations Density 0.009%

    No Known Activations