© 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. 77149
    Prev
    Next
    INDEX
    Explanations

    Code/technical/foreign context

    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
     left
    -0.44
    ghouse
    -0.43
    mar
    -0.41
    Matic
    -0.41
     ddelweddau
    -0.41
    goon
    -0.40
    marin
    -0.40
     catch
    -0.40
    greifen
    -0.39
    MAR
    -0.39
    POSITIVE LOGITS
    tvguidetime
    0.82
     engraçadas
    0.75
    TypedDataSet
    0.73
     comigo
    0.73
     conmigo
    0.70
    enderror
    0.69
     invokingState
    0.67
    AutoField
    0.66
    Étymologie
    0.66
    Further
    0.65
    Activations Density 0.001%

    No Known Activations