© 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. 0-CLT-HP
    7. 91128
    Prev
    Next
    INDEX
    Explanations

    years

    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
     on
    -0.42
     
    -0.41
     a
    -0.40
     the
    -0.40
     that
    -0.39
    .
    -0.39
     us
    -0.39
     “
    -0.38
    :
    -0.38
     "
    -0.38
    POSITIVE LOGITS
     متعلقه
    1.39
     المعيارى
    1.28
    principalTable
    1.22
     defaultstate
    1.21
    +#+#
    1.16
    tagHelperRunner
    1.10
    Autoritní
    1.10
    LookAnd
    1.05
     Мексичка
    1.05
    RenderAtEndOf
    1.05
    Activations Density 0.281%

    No Known Activations