© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 44166
    Prev
    Next
    INDEX
    Explanations

    but

    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
    ,
    -0.71
    .
    -0.66
    :
    -0.59
    /
    -0.59
     (
    -0.57
     can
    -0.57
     and
    -0.55
     I
    -0.55
    -
    -0.55
     but
    -0.54
    POSITIVE LOGITS
     itſelf
    1.51
     Majefty
    1.46
     myſelf
    1.46
    évaluateur
    1.38
     Monfieur
    1.33
     purpoſe
    1.31
     Shakspeare
    1.31
    ſelves
    1.30
     themſelves
    1.30
     Cæsar
    1.30
    Activations Density 0.220%

    No Known Activations