Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 91269
    Prev
    Next
    INDEX
    Explanations

    assertions

    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
    ness
    -1.28
     criticize
    -1.11
    NESS
    -1.09
     criticise
    -1.07
    ergies
    -1.05
     claim
    -1.05
     postulate
    -1.00
    🏾
    -0.96
     whine
    -0.96
     charge
    -0.95
    POSITIVE LOGITS
    e
    0.79
     the
    0.70
     for
    0.70
    ,
    0.68
     with
    0.67
     of
    0.66
     or
    0.65
     from
    0.65
     a
    0.65
     on
    0.64
    Activations Density 1.506%

    No Known Activations