© 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. 5-CLT-HP
    7. 1000
    Prev
    Next
    INDEX
    Explanations

    Raw text/code snippets

    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
     ribos
    -0.62
    DllImport
    -0.58
    Hozzáférés
    -0.57
    basicConfig
    -0.57
    ฒ
    -0.56
    forRoot
    -0.56
     manufactures
    -0.55
    )+"
    -0.54
    endregion
    -0.54
    vaar
    -0.54
    POSITIVE LOGITS
    Véxase
    0.52
    曖昧さ回避
    0.51
    #+#
    0.45
    parsedMessage
    0.45
    Kjelder
    0.44
    Personensuche
    0.44
    webElementGuid
    0.43
    CharArray
    0.41
     متحده
    0.41
    oredCriteria
    0.41
    Activations Density 0.001%

    No Known Activations