© 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. 77254
    Prev
    Next
    INDEX
    Explanations

    Technical/Specialized Topics

    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
    plates
    -0.59
    ConstraintMaker
    -0.56
     plates
    -0.53
    staticmethod
    -0.48
     cards
    -0.47
     kaarangay
    -0.47
    fillable
    -0.47
     supplier
    -0.47
    Ches
    -0.47
    supplier
    -0.46
    POSITIVE LOGITS
     TextInputType
    0.63
     betweenstory
    0.58
    ancers
    0.55
    dighet
    0.55
     embarazadas
    0.53
     NSObject
    0.53
     africains
    0.52
     bolig
    0.52
    onauts
    0.52
     marié
    0.51
    Activations Density 0.003%

    No Known Activations