© 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. 97665
    Prev
    Next
    INDEX
    Explanations

    return

    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
     return
    -1.33
     returning
    -1.17
    return
    -1.16
     returns
    -1.06
    returning
    -0.94
     Returning
    -0.89
    Returning
    -0.82
    situation
    -0.80
     retourne
    -0.77
     situation
    -0.75
    POSITIVE LOGITS
     مرئيه
    0.58
     autorytatywna
    0.52
     kasarigan
    0.51
     estekak
    0.51
    ThroughAttribute
    0.50
    ็จ
    0.49
     noted
    0.48
    viewDidLoad
    0.47
    ⓘ
    0.47
     piscinas
    0.46
    Activations Density 0.171%

    No Known Activations