© 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. 5-CLT-HP
    7. 3095
    Prev
    Next
    INDEX
    Explanations

    thinking or saying

    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
    出版年
    -0.65
    saraba
    -0.65
     estekak
    -0.51
     of
    -0.51
     referenties
    -0.50
     发表于
    -0.48
    μφωνα
    -0.47
    exitRule
    -0.47
    entire
    -0.47
    "]();
    -0.47
    POSITIVE LOGITS
    tvguidetime
    0.80
    runApp
    0.56
     that
    0.55
     Clow
    0.54
    lité
    0.53
    SuppressLint
    0.52
     Superhost
    0.51
    #
    0.51
    DrawerToggle
    0.50
    providedIn
    0.50
    Activations Density 0.015%

    No Known Activations