© 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. 91590
    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
    bootstrapcdn
    -0.76
    GraphicsUnit
    -0.71
    +:+
    -0.66
    出版年
    -0.65
    SequentialGroup
    -0.59
    wikidata
    -0.54
    ParallelGroup
    -0.53
    PageRoute
    -0.52
    AndEndTag
    -0.52
     '{@
    -0.50
    POSITIVE LOGITS
    ]$}
    0.57
    SharedDtor
    0.50
    eseorang
    0.48
     anaemia
    0.47
    extendable
    0.47
     surla
    0.46
     Efq
    0.46
     HasFactory
    0.44
     Всё
    0.44
    पया
    0.44
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.