© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 11440
    Prev
    Next
    INDEX
    Explanations

    volume

    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
     volume
    -1.45
    volume
    -1.34
     Volume
    -1.30
    Volume
    -1.20
     VOLUME
    -1.12
     volumes
    -1.05
    VOLUME
    -1.04
     Volumen
    -1.02
     Volumes
    -0.98
     volumen
    -0.98
    POSITIVE LOGITS
    WriteBarrier
    0.71
    PerformLayout
    0.69
     CURIAM
    0.68
    StoreMessageInfo
    0.60
     ویکی‌پدی
    0.59
     lenker
    0.59
     متعلقه
    0.59
    izations
    0.59
    GIH
    0.58
     SwitchCompat
    0.57
    Activations Density 0.019%

    No Known Activations