© 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. 1-CLT-HP
    7. 13096
    Prev
    Next
    INDEX
    Explanations

    endos

    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
    XmlType
    -0.56
     vPvB
    -0.55
    KommentareTeilen
    -0.54
     beginnetje
    -0.53
    GeoNames
    -0.52
    awtextra
    -0.52
    PYX
    -0.52
     Etern
    -0.52
    abstractmethod
    -0.52
     JpaRepository
    -0.50
    POSITIVE LOGITS
     meille
    0.58
     aikaa
    0.56
    vyšší
    0.55
     hauts
    0.54
    toHave
    0.53
     démocr
    0.52
     vostri
    0.52
    kan
    0.52
     nemici
    0.52
    webElement
    0.52
    Activations Density 0.086%

    No Known Activations