© 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. 0-CLT-HP
    7. 38730
    Prev
    Next
    INDEX
    Explanations

    Attempting actions

    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
    tagHelperRunner
    -1.31
     inspecting
    -0.99
     executing
    -0.96
     submitting
    -0.94
     שוליים
    -0.94
     saites
    -0.92
     BoxDecoration
    -0.91
     distributing
    -0.90
     reacting
    -0.90
     associating
    -0.89
    POSITIVE LOGITS
     one
    0.64
     a
    0.63
     real
    0.62
     the
    0.61
     potential
    0.58
     good
    0.57
     kind
    0.57
     data
    0.57
     legal
    0.57
     formal
    0.56
    Activations Density 0.049%

    No Known Activations