© 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. 92678
    Prev
    Next
    INDEX
    Explanations

    code

    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
    ælp
    -0.62
     Roskov
    -0.61
    ISupport
    -0.61
     interstate
    -0.60
     Laird
    -0.58
    ciutto
    -0.57
    ectl
    -0.57
     setCode
    -0.57
     feed
    -0.56
     lưới
    -0.55
    POSITIVE LOGITS
     typelib
    0.49
    sidemargin
    0.49
    createNewFile
    0.44
    XmlAccessType
    0.42
    logiques
    0.42
    ValueStyle
    0.40
    AsUp
    0.40
     closed
    0.39
    Açık
    0.38
    closed
    0.36
    Activations Density 0.001%

    No Known Activations