© 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. 9224
    Prev
    Next
    INDEX
    Explanations

    Dodge, Radar, excretion, Martinez

    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
    cretion
    -0.52
    onicus
    -0.52
    жа
    -0.52
     recognise
    -0.42
     okuyayım
    -0.41
     recognising
    -0.41
     mengen
    -0.40
     fora
    -0.40
     Gauss
    -0.40
    schwar
    -0.40
    POSITIVE LOGITS
    SourceChecksum
    0.85
     Meksiku
    0.74
    AccessorTable
    0.68
    ähkö
    0.67
    InitVars
    0.66
    principalTable
    0.63
    featureID
    0.63
    Geplaatst
    0.63
     незавершена
    0.63
    ſelf
    0.63
    Activations Density 0.007%

    No Known Activations