© 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. 1-CLT-HP
    7. 14965
    Prev
    Next
    INDEX
    Explanations

    C

    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
    \{\\
    -0.69
     pinulongan
    -0.60
     AssemblyProduct
    -0.55
    InSection
    -0.53
     piedras
    -0.53
    RectangleBorder
    -0.53
     ModelExpression
    -0.51
    Personensuche
    -0.48
    moveToNext
    -0.48
    ✨:
    -0.47
    POSITIVE LOGITS
    Jereo
    0.63
    shadowOpacity
    0.54
    Panamoan
    0.53
    gypti
    0.53
    nocchi
    0.51
    ⓧ
    0.50
    zzleHttp
    0.50
    usitis
    0.49
    esticular
    0.48
    vités
    0.48
    Activations Density 0.008%

    No Known Activations