© 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. 72920
    Prev
    Next
    INDEX
    Explanations

    Code/IT descriptions

    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
    jsxFileName
    -0.69
     الحره
    -0.66
     <<<<<<<<<<<<<<
    -0.66
     intptr
    -0.63
     uintptr
    -0.63
    StoreMessageInfo
    -0.59
     متعلقه
    -0.59
    }),
    -0.59
    parsedMessage
    -0.57
    RTEX
    -0.56
    POSITIVE LOGITS
    tisol
    0.49
     Catto
    0.47
     straight
    0.47
    straight
    0.45
    paravant
    0.45
     PLWABN
    0.41
    raulic
    0.41
     AttributeSet
    0.41
     IBM
    0.40
     évêque
    0.39
    Activations Density 0.002%

    No Known Activations