© 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. 0-CLT-HP
    7. 95334
    Prev
    Next
    INDEX
    Explanations

    mann

    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
    man
    -1.69
    MAN
    -1.55
     Man
    -1.48
    Man
    -1.45
    mann
    -1.30
    manni
    -1.26
    MANN
    -1.21
     MAN
    -1.19
     man
    -1.18
    mans
    -1.05
    POSITIVE LOGITS
    rungsseite
    0.61
     Realms
    0.60
     Confer
    0.59
    "]);
    0.57
     Framing
    0.57
    ")));
    0.57
     Kitchens
    0.56
     verily
    0.56
     Fairness
    0.56
    expandindo
    0.56
    Activations Density 0.444%

    No Known Activations