© 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. 38761
    Prev
    Next
    INDEX
    Explanations

    do

    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
    -1.04
    ValueStyle
    -1.03
    脚注の使い方
    -1.00
    Personensuche
    -0.99
     Monfieur
    -0.98
    styleType
    -0.97
     tartalomajánló
    -0.96
     doubtnut
    -0.95
     myſelf
    -0.94
     Pyrene
    -0.94
    POSITIVE LOGITS
     not
    0.82
     a
    0.82
     
    0.69
    <eos>
    0.69
     Not
    0.66
     what
    0.63
     an
    0.60
     so
    0.60
     un
    0.59
     as
    0.58
    Activations Density 0.035%

    No Known Activations