© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 97118
    Prev
    Next
    INDEX
    Explanations

    Objective

    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
     inside
    -0.46
    aarrggbb
    -0.45
    inside
    -0.43
    bla
    -0.43
    arm
    -0.43
     bahay
    -0.43
    ViewStyle
    -0.42
    mass
    -0.42
    Trichlor
    -0.41
     CAS
    -0.40
    POSITIVE LOGITS
    ✨:
    0.74
    abestanden
    0.72
    mybatisplus
    0.68
     Audiodateien
    0.67
    */),
    0.65
    المناصب
    0.65
    
    0.65
    <?>>
    0.63
    
    0.62
    //
    0.59
    Activations Density 0.005%

    No Known Activations