© 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. 20-CLT-HP
    7. 75864
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act-logits · 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
     miss
    -0.60
     saw
    -0.57
    Portale
    -0.56
    cho
    -0.56
    toHexString
    -0.54
    principalColumn
    -0.50
     Dick
    -0.50
    derung
    -0.49
    êque
    -0.49
     OkHttpClient
    -0.47
    POSITIVE LOGITS
     passed
    0.64
    AndroidJUnit
    0.63
    EDEFAULT
    0.59
     passado
    0.58
    ChildScrollView
    0.56
    CloseOperation
    0.56
    ztály
    0.56
    MessageState
    0.54
     lenker
    0.54
     forKey
    0.54
    Activations Density 0.000%

    No Known Activations