© 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. 98087
    Prev
    Next
    INDEX
    Explanations

    backpack

    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
    jsonwebtoken
    -0.48
     néz
    -0.44
     démocratie
    -0.43
    oman
    -0.42
    mAh
    -0.42
    __':
    -0.41
    TBD
    -0.40
     gordura
    -0.40
    guém
    -0.39
    mm
    -0.39
    POSITIVE LOGITS
    NameInMap
    0.82
    Personensuche
    0.81
     חיצוניים
    0.73
    oa̍t
    0.72
     <=",
    0.71
    MemoryWarning
    0.71
     Савезне
    0.71
    GEBURTSDATUM
    0.68
    WebElementEntity
    0.68
    Eksterne
    0.67
    Activations Density 0.005%

    No Known Activations