© 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. 94963
    Prev
    Next
    INDEX
    Explanations

    fire

    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
     فريبيس
    -0.59
    MigrationBuilder
    -0.50
     NYPD
    -0.46
    WAII
    -0.46
    mapreduce
    -0.45
    manjaro
    -0.45
     ***!
    -0.44
    COUVER
    -0.44
    olesterol
    -0.44
    myModal
    -0.43
    POSITIVE LOGITS
    principalTable
    0.88
    Portale
    0.63
     autorytatywna
    0.61
    PerformLayout
    0.59
     ProtoMessage
    0.56
    igshid
    0.56
     δή
    0.56
    ///</
    0.55
     fidé
    0.55
    ########.
    0.54
    Activations Density 0.000%

    No Known Activations