© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 94513
    Prev
    Next
    INDEX
    Explanations

    inception

    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
    évaluateur
    -0.93
    UrlResolution
    -0.90
    ImageContext
    -0.86
    ьаж
    -0.77
    aarrggbb
    -0.76
    RenderAtEndOf
    -0.76
     Crafted
    -0.74
     crafted
    -0.71
    
    -0.70
     سكانية
    -0.69
    POSITIVE LOGITS
    ed
    0.72
    ment
    0.69
    ged
    0.60
    tal
    0.57
    JMenuItem
    0.53
    อย
    0.52
    d
    0.51
    ig
    0.51
    ty
    0.51
    sic
    0.51
    Activations Density 0.311%

    No Known Activations