© 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. 45694
    Prev
    Next
    INDEX
    Explanations

    so

    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
     confocal
    -0.56
     unknownFields
    -0.55
    joba
    -0.52
    titleMargin
    -0.52
    LookAnd
    -0.51
     sherds
    -0.51
     defStyleAttr
    -0.51
     olfactory
    -0.50
    +#+
    -0.50
    webElementXpaths
    -0.50
    POSITIVE LOGITS
    судар
    0.52
     Palestinians
    0.49
    ingroup
    0.48
     esternos
    0.48
     AssemblyTitle
    0.47
    umet
    0.47
     Homeland
    0.46
    fraz
    0.46
    grano
    0.44
    ghalaya
    0.43
    Activations Density 0.018%

    No Known Activations