© 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. 0-CLT-HP
    7. 43581
    Prev
    Next
    INDEX
    Explanations

    validation

    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
     spend
    -0.80
    FormTagHelper
    -0.54
     span
    -0.54
     fieldNum
    -0.54
    CIOS
    -0.52
     سكانية
    -0.51
    География
    -0.51
    featureID
    -0.50
    FieldBuilder
    -0.49
    ViewFeatures
    -0.47
    POSITIVE LOGITS
     beſt
    0.82
     pleaſure
    0.80
     thoſe
    0.79
     purpoſe
    0.79
     ſtate
    0.79
     ſche
    0.79
     houſe
    0.79
     ſtre
    0.77
     occaf
    0.77
     itſelf
    0.77
    Activations Density 0.143%

    No Known Activations