© 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. 90984
    Prev
    Next
    INDEX
    Explanations

    Technical/scientific processes

    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
     étoit
    -1.18
     marquées
    -1.16
     feroit
    -1.16
     avoient
    -1.13
     auroit
    -1.13
     réguli
    -1.12
     anún
    -1.12
     âgées
    -1.12
     vectorielles
    -1.11
     étoient
    -1.10
    POSITIVE LOGITS
     by
    1.19
     up
    0.85
     with
    0.79
     in
    0.78
     into
    0.77
     out
    0.71
     off
    0.71
     back
    0.70
     on
    0.69
     
    0.66
    Activations Density 1.539%

    No Known Activations