© 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. 4-CLT-HP
    7. 239
    Prev
    Next
    INDEX
    Explanations

    on

    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
     actionMode
    -0.67
     '\\;'
    -0.64
     كومونز
    -0.55
    ThemeOverlay
    -0.54
     defaultstate
    -0.54
    "]);
    -0.53
    @[+][
    -0.53
    ]-->
    -0.52
     gynhyrchwyd
    -0.52
    elemField
    -0.52
    POSITIVE LOGITS
     Cientí
    0.55
     Ecol
    0.53
    TagHelper
    0.53
     nakalista
    0.52
    Parcelize
    0.51
    KommentareTeilen
    0.51
     Feminism
    0.50
     Ecology
    0.50
     noin
    0.50
     Hydrology
    0.49
    Activations Density 0.003%

    No Known Activations