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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 97544
    Prev
    Next
    INDEX
    Explanations

    issues/questions/concerns

    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
    ]='\
    -0.55
     Global
    -0.46
    UnitTesting
    -0.45
     {}),
    -0.45
    Global
    -0.45
     nameless
    -0.44
    ToMany
    -0.44
    nonatomic
    -0.44
    HasIndex
    -0.44
    abstractmethod
    -0.43
    POSITIVE LOGITS
     HomeComponent
    0.66
     LUMP
    0.60
     during
    0.58
    发表于
    0.58
    basicConfig
    0.56
    TintMode
    0.56
     LoginPage
    0.55
     Wikimedijinoj
    0.55
     isInitialized
    0.54
    tinyos
    0.54
    Activations Density 0.003%

    No Known Activations