© 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. 0-CLT-HP
    7. 40037
    Prev
    Next
    INDEX
    Explanations

    biscuits

    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
     Facing
    -0.63
    Facing
    -0.58
    wyd
    -0.54
     out
    -0.54
     Under
    -0.52
    icorn
    -0.50
     under
    -0.50
     Perce
    -0.50
    under
    -0.49
    hace
    -0.49
    POSITIVE LOGITS
    OGND
    0.84
    Personendaten
    0.81
     nahilalakip
    0.79
    /**
    0.76
    WireFormatLite
    0.76
     Roskov
    0.75
     PyLong
    0.72
    NUMX
    0.69
    UTELY
    0.68
     通販
    0.68
    Activations Density 1.028%

    No Known Activations