© 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. 45719
    Prev
    Next
    INDEX
    Explanations

    -

    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
    RenderAtEndOf
    -1.16
    Personensuche
    -1.03
     Normdatei
    -0.95
    IsMutable
    -0.91
    rungsseite
    -0.91
     resourceCulture
    -0.89
     Theſe
    -0.87
    __':
    -0.80
     Italijanski
    -0.80
     <=",
    -0.79
    POSITIVE LOGITS
    ,
    0.53
     
    0.52
     M
    0.47
     (
    0.46
    (
    0.45
     as
    0.44
    PyObject
    0.44
     a
    0.44
     B
    0.44
    PROVID
    0.44
    Activations Density 0.022%

    No Known Activations