© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 97045
    Prev
    Next
    INDEX
    Explanations

    of

    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
     stages
    -0.58
    Становништво
    -0.56
    InjectAttribute
    -0.56
    igshid
    -0.56
    AndEndTag
    -0.55
     finalmente
    -0.53
    Phases
    -0.53
    مرحله
    -0.52
    的过程
    -0.52
     stage
    -0.52
    POSITIVE LOGITS
     disambiguazione
    0.59
     skú
    0.57
    matchCondition
    0.57
    zitter
    0.55
     attacco
    0.51
    cinia
    0.50
     NSCoder
    0.49
    MemoryWarning
    0.48
     싶
    0.48
    rungsseite
    0.48
    Activations Density 0.006%

    No Known Activations