© 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. 1-CLT-HP
    7. 516
    Prev
    Next
    INDEX
    Explanations

    easier

    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
     BoxDecoration
    -0.79
    mobileqq
    -0.65
     Normdatei
    -0.65
    AnchorStyles
    -0.65
    verton
    -0.65
    WithMany
    -0.63
     BorderSide
    -0.63
    Clik
    -0.61
     مشين
    -0.59
    quias
    -0.56
    POSITIVE LOGITS
     said
    1.02
     stated
    0.77
    said
    0.76
    Said
    0.74
     talked
    0.68
     explained
    0.68
     SAID
    0.66
    stated
    0.65
     done
    0.64
     carried
    0.62
    Activations Density 0.005%

    No Known Activations