© 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. 0-CLT-HP
    7. 94982
    Prev
    Next
    INDEX
    Explanations

    Web page snippets

    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
     Efe
    -0.57
     grades
    -0.49
    甸
    -0.48
    र्
    -0.47
     open
    -0.47
     proxies
    -0.46
    entin
    -0.45
     respondent
    -0.45
     Oph
    -0.45
    Efe
    -0.45
    POSITIVE LOGITS
    WireFormatLite
    0.84
     surla
    0.77
    OGND
    0.73
     noDo
    0.71
    RUnlock
    0.70
    setVerticalGroup
    0.68
    PRNewswire
    0.65
     resourceCulture
    0.63
    IndentedString
    0.62
    arraycopy
    0.62
    Activations Density 1.664%

    No Known Activations