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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 12649
    Prev
    Next
    INDEX
    Explanations

    to

    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
     introduce
    -0.81
     be
    -0.67
     do
    -0.60
     expose
    -0.60
     create
    -0.60
     reach
    -0.59
     bring
    -0.59
     get
    -0.59
     make
    -0.58
     have
    -0.57
    POSITIVE LOGITS
    ArgsConstructor
    0.79
     ſeveral
    0.76
     auroit
    0.72
     ſmall
    0.69
     poffible
    0.69
     greateſt
    0.69
     feroit
    0.66
     définiti
    0.66
     theſe
    0.66
     fevere
    0.65
    Activations Density 0.043%

    No Known Activations