© 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. 4-CLT-HP
    7. 3357
    Prev
    Next
    INDEX
    Explanations

    URL

    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
    تقاوى
    -0.72
    ükemmel
    -0.67
    GOTREF
    -0.67
     nahilalakip
    -0.66
     виправивши
    -0.65
    ]--;
    -0.63
    AsUp
    -0.62
     CreateTagHelper
    -0.62
    HostException
    -0.62
    RTSC
    -0.61
    POSITIVE LOGITS
    ://
    0.48
     //$
    0.43
    sk
    0.41
    ::<
    0.40
    ::-
    0.39
    setImageBitmap
    0.39
    íz
    0.39
    
    0.38
    [--
    0.38
     "__
    0.37
    Activations Density 0.109%

    No Known Activations