© 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. 836
    Prev
    Next
    INDEX
    Explanations

    timezones and 'continued' indicators

    np_max-act · gemini-2.0-flash
    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
    IonicModule
    -0.56
    PreExecute
    -0.52
    })->
    -0.48
     whim
    -0.47
    OMON
    -0.46
    ViewFeatures
    -0.46
     numberOfRows
    -0.46
     bottleneck
    -0.45
    UrlResolution
    -0.45
    __":
    -0.45
    POSITIVE LOGITS
    WebElementEntity
    0.68
    Hochspringen
    0.59
     Administrativna
    0.58
     öv
    0.58
    çar
    0.54
     []:
    0.53
     procedimientos
    0.53
    OCCURRED
    0.53
    Skocz
    0.52
     useAppContext
    0.52
    Activations Density 0.006%

    No Known Activations