© 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. 1-CLT-HP
    7. 14751
    Prev
    Next
    INDEX
    Explanations

    all

    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
     فريبيس
    -0.79
    astify
    -0.77
     ujednoznacz
    -0.68
    Datuak
    -0.66
     disambiguazione
    -0.66
     Normdatei
    -0.65
    __":
    -0.62
     snippetHide
    -0.61
    +#+#
    -0.60
    SharedCtor
    -0.60
    POSITIVE LOGITS
    دانشنامهٔ
    0.55
    Geplaatst
    0.50
     constancy
    0.49
    OutputType
    0.48
    下载附件
    0.47
     terrorism
    0.46
     U
    0.45
     ModelExpression
    0.44
    ftagPool
    0.44
    かは
    0.44
    Activations Density 0.009%

    No Known Activations