© 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. 96727
    Prev
    Next
    INDEX
    Explanations

    storage

    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
     in
    -0.57
    метра
    -0.51
    Nets
    -0.45
     Cent
    -0.45
     Ent
    -0.44
     ent
    -0.44
    neta
    -0.44
     g
    -0.44
    поро
    -0.44
    enta
    -0.43
    POSITIVE LOGITS
    MigrationBuilder
    0.82
     itſelf
    0.76
    \{\\
    0.76
     Monfieur
    0.74
    awtextra
    0.73
     Houſe
    0.73
     Theſe
    0.71
    tvguidetime
    0.71
    CloseOperation
    0.68
     autorytatywna
    0.68
    Activations Density 0.004%

    No Known Activations