© 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. 15514
    Prev
    Next
    INDEX
    Explanations

    hyphen

    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
    adpleegd
    -0.64
    GEBURTSDATUM
    -0.61
    olingo
    -0.60
    OrBuilder
    -0.60
    MessageOf
    -0.58
    -
    -0.58
    Personendaten
    -0.58
    )))));
    -0.57
    atiles
    -0.56
     propOrder
    -0.56
    POSITIVE LOGITS
    to
    0.54
    Hour
    0.45
     africains
    0.45
    Party
    0.45
    part
    0.44
    Year
    0.44
    Way
    0.43
    pence
    0.42
    CORBA
    0.41
     to
    0.41
    Activations Density 0.018%

    No Known Activations