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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 982
    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
    BASEPATH
    -0.58
     tends
    -0.58
     ThemeData
    -0.50
    ISupport
    -0.50
     contains
    -0.49
    ี้ยง
    -0.48
    gunas
    -0.48
    inese
    -0.48
    सन्दर्भ
    -0.47
    belongsTo
    -0.46
    POSITIVE LOGITS
     ModelExpression
    0.71
    RenderAtEndOf
    0.69
     resourceCulture
    0.63
    AccessorTable
    0.62
    SequentialGroup
    0.62
    OGND
    0.58
     AssemblyCompany
    0.57
    NewReader
    0.56
    XmlEnum
    0.55
    ]";
    0.53
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.