© 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. 20-CLT-HP
    7. 77304
    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
     remplissage
    -0.46
     High
    -0.43
     Large
    -0.43
     Passes
    -0.41
    High
    -0.41
     registre
    -0.40
     cálculos
    -0.40
    opold
    -0.40
     périph
    -0.40
     Curves
    -0.40
    POSITIVE LOGITS
    PreferredItem
    0.97
    ьаж
    0.89
     صوتيه
    0.82
    MessageOf
    0.82
    GEBURTSDATUM
    0.81
     intptr
    0.79
    OGND
    0.73
    verwijspagina
    0.72
    WriteTagHelper
    0.72
    MigrationBuilder
    0.71
    Activations Density 0.000%

    No Known Activations