© 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. 4-CLT-HP
    7. 4495
    Prev
    Next
    INDEX
    Explanations

    esch

    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
    fromCharCode
    -0.59
    jsonwebtoken
    -0.52
    objc
    -0.51
     Lacrosse
    -0.50
    PasswordField
    -0.50
     Neuro
    -0.48
     jellyfish
    -0.46
    avits
    -0.46
    athione
    -0.45
     neuro
    -0.44
    POSITIVE LOGITS
    RenderAtEndOf
    0.68
    RegressionTest
    0.64
    AsUp
    0.62
     Monfieur
    0.59
    webElementXpaths
    0.58
    providedIn
    0.57
     magasiner
    0.56
    butuhkan
    0.56
    jsxFileName
    0.55
    !*\
    0.55
    Activations Density 0.001%

    No Known Activations