© 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. 5-CLT-HP
    7. 91490
    Prev
    Next
    INDEX
    Explanations

    ostom

    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
    ostom
    -1.23
     Signalez
    -0.77
    transQ
    -0.67
     المعيارى
    -0.60
    fromnode
    -0.60
     Infórmanos
    -0.56
     الدولى
    -0.56
    afficheront
    -0.55
     समीक्षाओं
    -0.54
    BufferException
    -0.52
    POSITIVE LOGITS
    migrationBuilder
    0.65
    Бахар
    0.56
    ronpa
    0.54
    voirs
    0.53
    orrhea
    0.50
    adə
    0.48
    escent
    0.48
     Proof
    0.47
    ός
    0.47
     pray
    0.47
    Activations Density 0.000%

    No Known Activations