© 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. 91195
    Prev
    Next
    INDEX
    Explanations

    legal/political cases

    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
    alised
    -0.54
    CheckedChanged
    -0.53
    RegressionTest
    -0.52
    </em>
    -0.49
     setMessage
    -0.47
    Nemo
    -0.47
     đen
    -0.47
    спита
    -0.47
    hikari
    -0.45
    amship
    -0.45
    POSITIVE LOGITS
     BoxFit
    0.72
    Lähteet
    0.71
    
    0.67
    tonode
    0.67
    تقاوى
    0.65
    出版年
    0.65
     WaitForSeconds
    0.65
    ualmente
    0.63
     &___
    0.63
     المعيارى
    0.63
    Activations Density 1.252%

    No Known Activations