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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 97463
    Prev
    Next
    INDEX
    Explanations

    impulse

    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
    Imp
    -1.12
     Imp
    -1.05
    imp
    -1.05
     Impulse
    -1.05
     impulse
    -0.96
     impulses
    -0.83
     GenerationType
    -0.79
     Purposes
    -0.79
    DockStyle
    -0.79
     imp
    -0.75
    POSITIVE LOGITS
     энциклопедия
    0.58
    thereum
    0.56
    akura
    0.49
    يميديا
    0.49
    xtype
    0.49
    soo
    0.48
    istar
    0.48
    lehre
    0.47
    }\]
    0.47
    --}}
    0.47
    Activations Density 0.118%

    No Known Activations