© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 94962
    Prev
    Next
    INDEX
    Explanations

    h

    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
    WireFormatLite
    -0.84
     unknownFields
    -0.77
    FieldBuilder
    -0.77
    Билгалдахарш
    -0.68
     ProtoMessage
    -0.68
    Hochspringen
    -0.67
    BagLayout
    -0.67
    DockStyle
    -0.67
    AndEndTag
    -0.67
     незавершена
    -0.66
    POSITIVE LOGITS
     âgées
    0.45
     berätt
    0.43
     équip
    0.41
     dévelo
    0.40
    Espèce
    0.39
     aéro
    0.38
     mécan
    0.38
     pauvres
    0.37
     alimentaire
    0.37
     morrer
    0.37
    Activations Density 0.000%

    No Known Activations