© 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. 91407
    Prev
    Next
    INDEX
    Explanations

    documents

    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
    tagHelperRunner
    -0.70
     ©️
    -0.66
     صوتيه
    -0.64
    XMLSchema
    -0.59
     الحره
    -0.58
    AndEndTag
    -0.55
    __(/*!
    -0.55
     виправивши
    -0.54
    Copyright
    -0.54
     makeStyles
    -0.53
    POSITIVE LOGITS
     Mühe
    0.51
     prossimo
    0.50
    ikyuu
    0.46
    стори
    0.44
    Qs
    0.43
    arita
    0.43
    hical
    0.42
    jsxFileName
    0.42
    ÍS
    0.42
    InOut
    0.41
    Activations Density 0.005%

    No Known Activations