© 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. 20-CLT-HP
    7. 74561
    Prev
    Next
    INDEX
    Explanations

    .

    np_max-act-logits · 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
    AnchorStyles
    -0.80
     springfox
    -0.63
     estekak
    -0.61
     disambiguazione
    -0.59
    VIAF
    -0.57
    ">//
    -0.56
    colhead
    -0.53
     autorytatywna
    -0.52
     fuer
    -0.50
    elemField
    -0.50
    POSITIVE LOGITS
    ftagPool
    0.51
    UAGES
    0.50
    دانشنامهٔ
    0.46
    TagHelpers
    0.45
    rophes
    0.45
    UrlResolution
    0.44
     Luk
    0.42
    PDOException
    0.42
     Spandex
    0.42
    getDoctrine
    0.42
    Activations Density 0.000%

    No Known Activations