© 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. 20-CLT-HP
    7. 74723
    Prev
    Next
    INDEX
    Explanations

    code/programming

    np_max-act-logits · 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
     is
    -0.68
     was
    -0.61
     Comprometido
    -0.61
     split
    -0.58
     drain
    -0.58
     stretch
    -0.58
    providedIn
    -0.57
    queryInterface
    -0.56
    XmlAccessType
    -0.55
     >>=
    -0.55
    POSITIVE LOGITS
    הערות
    0.56
     Inv
    0.53
    Dislikes
    0.51
     Disp
    0.50
    SPATH
    0.49
     Subs
    0.49
     Integr
    0.49
     probes
    0.49
     Probes
    0.48
     Ens
    0.48
    Activations Density 0.003%

    No Known Activations