© 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. 20-CLT-HP
    7. 73784
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Hozzáférés
    -0.61
    >');
    -0.54
    seen
    -0.53
     Freeway
    -0.52
     penser
    -0.50
    ponses
    -0.48
    "]];
    -0.48
     Scale
    -0.47
    yeron
    -0.47
    狈
    -0.46
    POSITIVE LOGITS
    DockStyle
    0.63
    AutoField
    0.62
     finds
    0.62
     propOrder
    0.61
     lenker
    0.56
    Finding
    0.56
     Paglinawan
    0.56
     surfaces
    0.54
     flaring
    0.54
     finding
    0.53
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.