© 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. 38737
    Prev
    Next
    INDEX
    Explanations

    software setting/implementation

    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
     Efq
    -0.83
    Ссылки
    -0.69
     réglable
    -0.69
     Keeping
    -0.67
     vectorielle
    -0.66
    LookAnd
    -0.64
     vectorielles
    -0.64
     pinulongan
    -0.63
     citoy
    -0.62
     cysts
    -0.61
    POSITIVE LOGITS
    VersionUID
    0.54
    पया
    0.51
     Us
    0.48
     Id
    0.47
    boro
    0.47
     enter
    0.47
     conta
    0.46
    stück
    0.45
    Ви
    0.45
     d
    0.45
    Activations Density 0.011%

    No Known Activations