Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 1895
    Prev
    Next
    INDEX
    Explanations

    of

    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
     of
    -0.63
    Népesség
    -0.61
    ROLE
    -0.49
     respeito
    -0.48
    Filmo
    -0.47
    routeProvider
    -0.47
     âmes
    -0.45
     role
    -0.45
     aikana
    -0.44
     about
    -0.44
    POSITIVE LOGITS
    #
    0.78
    LookAnd
    0.73
    ModelAdmin
    0.71
     JpaRepository
    0.68
    RegressionTest
    0.65
    stdc
    0.63
    ształ
    0.62
    tagHelperRunner
    0.59
    ActionCreators
    0.57
    ']>;
    0.56
    Activations Density 0.004%

    No Known Activations