© 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. 5-CLT-HP
    7. 91601
    Prev
    Next
    INDEX
    Explanations

    external

    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
     batte
    -0.48
    (',')
    -0.45
    (",")
    -0.45
    ここでは
    -0.44
    ghorn
    -0.43
    שט
    -0.43
    ugh
    -0.43
    riever
    -0.43
    gate
    -0.42
    Bats
    -0.42
    POSITIVE LOGITS
    +#+
    0.73
    GEBURTSDATUM
    0.69
     odkazy
    0.69
     JpaRepository
    0.69
    +:+
    0.67
    contentLoaded
    0.67
     وتسجيلات
    0.65
     <=",
    0.64
    abestanden
    0.63
    protoimpl
    0.63
    Activations Density 0.042%

    No Known Activations