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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 38819
    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
     antaranya
    -0.59
    Sklici
    -0.57
     CATCH
    -0.53
     oreille
    -0.51
    atoon
    -0.50
    ProgressHUD
    -0.50
    Poloha
    -0.50
    complexType
    -0.50
    ulement
    -0.49
    xil
    -0.49
    POSITIVE LOGITS
    gebir
    0.61
     يتيمه
    0.61
     مشين
    0.60
     الحره
    0.60
    ssaint
    0.59
    一亮
    0.57
    orija
    0.56
    RectangleBorder
    0.56
    aturi
    0.55
    プリング
    0.55
    Activations Density 0.112%

    No Known Activations