© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 39893
    Prev
    Next
    INDEX
    Explanations

    0

    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
     enfans
    -1.15
     avoient
    -1.13
     étoient
    -1.11
     dieux
    -1.09
     Grecs
    -1.05
     ouvriers
    -1.04
     prêtres
    -1.04
     cérami
    -1.02
     preuves
    -1.02
     démocr
    -1.01
    POSITIVE LOGITS
    ,
    1.39
    -
    1.18
    .
    1.02
     and
    0.96
     to
    0.94
    /
    0.89
    :
    0.88
     or
    0.87
    %
    0.87
    ;
    0.84
    Activations Density 1.441%

    No Known Activations