© 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. 5-CLT-HP
    7. 2126
    Prev
    Next
    INDEX
    Explanations

    opportunities

    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
    Спасылкі
    -0.59
    soever
    -0.55
     tiroirs
    -0.52
     of
    -0.48
    tól
    -0.48
     preuves
    -0.48
    endphp
    -0.47
     tendances
    -0.47
    Enlaces
    -0.47
    by
    -0.47
    POSITIVE LOGITS
     for
    0.75
     Roskov
    0.60
     exist
    0.58
     exists
    0.56
     existed
    0.56
    IBOutlet
    0.51
    findpost
    0.51
    ouren
    0.51
     abound
    0.51
    jsxFileName
    0.51
    Activations Density 0.000%

    No Known Activations