© 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
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 45556
    Prev
    Next
    INDEX
    Explanations

    udian

    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
     JMenuItem
    -0.62
    ObjectContext
    -0.58
    Amicalement
    -0.54
    ümer
    -0.52
     onAnimation
    -0.52
    RequestMapping
    -0.52
    MotionEvent
    -0.51
    openConnection
    -0.50
     '\\;'
    -0.50
    >_
    -0.50
    POSITIVE LOGITS
    ########.
    0.53
    istre
    0.52
    تقاوى
    0.52
     transfieras
    0.50
    Claw
    0.48
    })));
    0.48
    ddots
    0.47
     nahilalakip
    0.47
    Билгалдахарш
    0.46
     صوتيه
    0.45
    Activations Density 0.012%

    No Known Activations