© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 71599
    Prev
    Next
    INDEX
    Explanations

    Names, code, and references

    np_max-act-logits · 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
    ActionCreators
    -0.70
    UnsafeEnabled
    -0.60
    Tikang
    -0.58
    RTDA
    -0.58
    RTLU
    -0.57
    SpringRunner
    -0.56
    aunt
    -0.55
    StructEnd
    -0.55
    äher
    -0.54
    pherd
    -0.54
    POSITIVE LOGITS
     MediaType
    0.43
     Yol
    0.43
     références
    0.43
     minOccurs
    0.43
    Demografía
    0.42
    béco
    0.41
     yc
    0.41
     Wickham
    0.41
     חיצוניים
    0.40
     snippetHide
    0.39
    Activations Density 0.001%

    No Known Activations