© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 96482
    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
    stdc
    -0.52
    TagMode
    -0.49
     createState
    -0.47
    saraba
    -0.47
    āya
    -0.45
     Trail
    -0.43
    यी
    -0.42
    สม
    -0.41
     may
    -0.41
     pisze
    -0.41
    POSITIVE LOGITS
    UnknownFields
    0.63
     Deeper
    0.59
     SwitchCompat
    0.56
     AssemblyCulture
    0.56
    migrationBuilder
    0.56
     transfieras
    0.54
    /***/
    0.53
    )});
    0.51
    ✨:
    0.50
     Roskov
    0.50
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.