© 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. 5-CLT-HP
    4. 1222
    Prev
    Next
    INDEX
    Explanations

    of

    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
     Majefty
    -0.84
     itſelf
    -0.83
    )"),
    -0.83
    RenderAtEndOf
    -0.79
    %");
    -0.78
    )");
    
    -0.77
    ſelf
    -0.77
    PerformLayout
    -0.76
     AssemblyCulture
    -0.75
    '},
    
    -0.72
    POSITIVE LOGITS
     v
    0.51
     U
    0.44
    U
    0.44
    VS
    0.41
     technology
    0.41
    v
    0.41
    <eos>
    0.40
     told
    0.40
     survival
    0.39
    .
    0.38
    Activations Density 0.000%

    No Known Activations