© 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. 9792
    Prev
    Next
    INDEX
    Explanations

    northern or southern

    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
    southern
    -0.55
     ch
    -0.53
    northern
    -0.52
    kopf
    -0.47
    пова
    -0.45
    slo
    -0.45
    webElementGuid
    -0.45
    Externé
    -0.43
     الإنترنت
    -0.43
    south
    -0.43
    POSITIVE LOGITS
     itſelf
    0.83
     myſelf
    0.81
     whoſe
    0.77
    RUnlock
    0.75
     Anſ
    0.75
     Theſe
    0.71
     Eſ
    0.71
     whofe
    0.69
    UnknownFields
    0.68
    TemporalType
    0.66
    Activations Density 0.023%

    No Known Activations