© 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. 42407
    Prev
    Next
    INDEX
    Explanations

    atherosclerosis

    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
    inians
    -0.97
     calendriers
    -0.75
     tartalomajánló
    -0.67
    inian
    -0.66
    ValueStyle
    -0.65
    protoimpl
    -0.65
     GIPHY
    -0.64
     дописавши
    -0.62
     beginnetje
    -0.60
    awtextra
    -0.60
    POSITIVE LOGITS
    Παραπομπές
    0.54
    بيب
    0.48
    écnicas
    0.47
    isyon
    0.47
    ///</
    0.46
    collant
    0.45
    ities
    0.44
    MoveNext
    0.44
    jangan
    0.44
    ніципалі
    0.43
    Activations Density 0.442%

    No Known Activations