© 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. 1171
    Prev
    Next
    INDEX
    Explanations

    description of embodiments

    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
     board
    -1.22
     boards
    -1.17
     Board
    -0.98
     Boards
    -0.96
     BOARD
    -0.88
     stages
    -0.88
     boarded
    -0.84
    ArgsConstructor
    -0.79
     stage
    -0.77
     Lordships
    -0.70
    POSITIVE LOGITS
     of
    0.69
     and
    0.50
    aus
    0.50
    giving
    0.45
    back
    0.45
    y
    0.45
     or
    0.45
    a
    0.45
    Chham
    0.44
    plus
    0.44
    Activations Density 0.039%

    No Known Activations