© 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. 5-CLT-HP
    7. 95198
    Prev
    Next
    INDEX
    Explanations

    code

    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
    styleType
    -0.51
     fémin
    -0.47
    SharedDtor
    -0.47
     préféré
    -0.46
     كومونز
    -0.45
    saraba
    -0.45
     ]];
    -0.44
    ";}
    -0.44
    <%@
    -0.43
     préf
    -0.43
    POSITIVE LOGITS
     صوتيه
    0.67
    ljeno
    0.59
    ταν
    0.57
    FormTagHelper
    0.56
    tagHelperRunner
    0.56
    quine
    0.56
    WebServlet
    0.56
    kmale
    0.55
    JG
    0.54
    astéroïdes
    0.54
    Activations Density 0.004%

    No Known Activations