© 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. 9174
    Prev
    Next
    INDEX
    Explanations

    list

    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
     felicità
    -0.62
    StructEnd
    -0.51
     sufferers
    -0.51
     tabernacle
    -0.50
    ábor
    -0.50
     detaine
    -0.49
     hostages
    -0.48
    ArrowToggle
    -0.48
     detainees
    -0.48
     autorità
    -0.47
    POSITIVE LOGITS
    awtextra
    0.63
     Trouver
    0.51
     pf
    0.51
    opsida
    0.50
     الاطلاع
    0.50
    iastes
    0.49
    DoubleQuotes
    0.48
    
    0.48
    رشف
    0.46
     numbers
    0.45
    Activations Density 0.006%

    No Known Activations