© 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. 4-CLT-HP
    7. 3306
    Prev
    Next
    INDEX
    Explanations

    neuro

    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
     defaultstate
    -0.53
     essai
    -0.48
     SAMPLING
    -0.47
     Sampling
    -0.46
     Synthesis
    -0.46
    PropertyGroup
    -0.46
     Organs
    -0.45
     FREQUENCY
    -0.45
     şə
    -0.45
     tỉnh
    -0.45
    POSITIVE LOGITS
    enumi
    0.63
    awtextra
    0.62
     BorderRadius
    0.61
    findpost
    0.60
    PSI
    0.57
    aarrggbb
    0.54
    ILD
    0.53
     MainAxisSize
    0.53
     تانيه
    0.53
    seteq
    0.50
    Activations Density 0.003%

    No Known Activations