© 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. 1-CLT-HP
    7. 12247
    Prev
    Next
    INDEX
    Explanations

    part, is

    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
     ones
    -0.47
     tools
    -0.45
     stations
    -0.40
     actors
    -0.40
     exercises
    -0.39
     scales
    -0.39
     sheds
    -0.38
     shed
    -0.37
     resolutions
    -0.37
     setters
    -0.37
    POSITIVE LOGITS
     continúas
    0.84
    RenderAtEndOf
    0.81
    存于互联网档案馆
    0.81
     initComponents
    0.75
    IsContent
    0.74
    ipelago
    0.74
     nahilalakip
    0.74
     autorytatywna
    0.73
    Referanser
    0.71
    principalColumn
    0.71
    Activations Density 0.005%

    No Known Activations