© 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. 1-CLT-HP
    7. 9013
    Prev
    Next
    INDEX
    Explanations

    Geographic locations/groups/politics

    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
    <bos>
    -0.71
    Geplaatst
    -0.52
     ""],
    -0.47
     popoli
    -0.46
    }*/
    -0.45
    reactivex
    -0.44
    CreateMap
    -0.43
     gefallen
    -0.43
     StatefulWidget
    -0.42
    lido
    -0.42
    POSITIVE LOGITS
    BagConstraints
    0.74
    matchCondition
    0.71
    SequentialGroup
    0.61
    makeConstraints
    0.60
    DoubleQuotes
    0.59
     gynhyrchwyd
    0.59
    FieldDescriptor
    0.58
     FBref
    0.57
    PageRoute
    0.54
     Kristi
    0.54
    Activations Density 0.019%

    No Known Activations