© 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. 0-CLT-HP
    7. 97276
    Prev
    Next
    INDEX
    Explanations

    balconies

    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
     Balance
    -1.31
     balance
    -1.14
     BALANCE
    -1.07
    Balance
    -0.97
    MigrationBuilder
    -0.81
    RegressionTest
    -0.77
    balance
    -0.75
    Jeografia
    -0.73
    BALANCE
    -0.70
    bastien
    -0.69
    POSITIVE LOGITS
     habl
    0.43
     pleasures
    0.42
     joys
    0.42
     singleton
    0.41
     puffs
    0.41
     haunts
    0.41
     ghost
    0.40
     produttore
    0.40
     delights
    0.39
    osoma
    0.39
    Activations Density 0.046%

    No Known Activations