© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 1915
    Prev
    Next
    INDEX
    Explanations

    involvement

    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
     préf
    -0.66
    anthene
    -0.58
     Personne
    -0.57
    цездатний
    -0.55
     préféré
    -0.54
    UNIDENTIFIED
    -0.53
    latego
    -0.53
     scanner
    -0.52
     municípios
    -0.52
     mommy
    -0.51
    POSITIVE LOGITS
     ErrIntOverflow
    0.68
    KommentareTeilen
    0.64
    ︎
    0.57
    ist
    0.56
    hips
    0.56
     الاطلاع
    0.55
    yntaxException
    0.54
    AndEndTag
    0.54
     насељу
    0.54
    theless
    0.53
    Activations Density 0.069%

    No Known Activations