© 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. 40033
    Prev
    Next
    INDEX
    Explanations

    math and code

    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
    кономі
    -0.59
     gratuits
    -0.53
     andererseits
    -0.52
    chanan
    -0.51
    legen
    -0.49
    GetEnumerator
    -0.49
     médical
    -0.49
     начало
    -0.49
    ooplankton
    -0.48
    reiten
    -0.48
    POSITIVE LOGITS
    ⓧ
    0.71
    PageContext
    0.65
    قایناق‌لار
    0.63
    djangoproject
    0.58
     Comprometido
    0.56
     referenties
    0.56
    WebVitals
    0.55
    })]
    0.54
    ANSA
    0.54
    HeaderText
    0.54
    Activations Density 0.153%

    No Known Activations