© 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. 5-CLT-HP
    7. 91462
    Prev
    Next
    INDEX
    Explanations

    himself

    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
     by
    -0.54
     oleh
    -0.45
     pela
    -0.44
     
    -0.40
     بواسطة
    -0.40
     tecn
    -0.40
     пользователем
    -0.38
     massive
    -0.37
     do
    -0.37
     ac
    -0.37
    POSITIVE LOGITS
    zzleHttp
    0.96
    ViewFeatures
    0.96
    ValueStyle
    0.93
    IntoConstraints
    0.92
     wireType
    0.90
    SBATCH
    0.89
     дописавши
    0.88
    
    0.88
    NUMX
    0.86
     AspNetCore
    0.86
    Activations Density 0.050%

    No Known Activations