© 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. 4809
    Prev
    Next
    INDEX
    Explanations

    technical/scientific descriptions

    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
     estekak
    -0.79
    makeConstraints
    -0.72
    tagHelperRunner
    -0.71
     SwitchCompat
    -0.70
     跳转至
    -0.69
    AnchorStyles
    -0.69
    awtextra
    -0.68
    ,‎
    -0.67
     <<<<<<<<<<<<<<
    -0.67
    RenderAtEndOf
    -0.65
    POSITIVE LOGITS
     ويكيميديا
    0.48
    Viki
    0.46
    ölker
    0.46
    новниш
    0.42
     húmedo
    0.41
    Brainz
    0.39
     fédéral
    0.38
    édie
    0.38
    checksum
    0.38
     begge
    0.37
    Activations Density 0.005%

    No Known Activations