© 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. 75581
    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
    Hochspringen
    -0.69
     consultato
    -0.69
    SequentialGroup
    -0.67
     cuire
    -0.65
     CreateTagHelper
    -0.65
    脚注の使い方
    -0.65
     pinulongan
    -0.64
    Skocz
    -0.63
    principalColumn
    -0.63
     nahilalakip
    -0.63
    POSITIVE LOGITS
     marginal
    0.48
     bomb
    0.47
    yfikacja
    0.47
     de
    0.47
     flat
    0.45
    fiets
    0.43
     infer
    0.43
     cultiv
    0.42
     r
    0.42
     flatter
    0.42
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.