© 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. 38655
    Prev
    Next
    INDEX
    Explanations

    Direction North

    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
     Monfieur
    -0.97
     title
    -0.96
     título
    -0.88
    UrlResolution
    -0.88
     titolo
    -0.88
    OGND
    -0.86
    title
    -0.85
     north
    -0.85
     iſt
    -0.85
     itſelf
    -0.85
    POSITIVE LOGITS
    en
    0.54
    ,
    0.47
    ly
    0.47
     so
    0.47
     and
    0.47
    -
    0.46
     or
    0.45
    wards
    0.45
    less
    0.44
     an
    0.44
    Activations Density 0.086%

    No Known Activations