© 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. 5-CLT-HP
    7. 2049
    Prev
    Next
    INDEX
    Explanations

    ron

    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
     beginnetje
    -0.73
    Vidite
    -0.64
    
    -0.57
    findpost
    -0.52
    principalColumn
    -0.52
    yntaxException
    -0.50
    UpInside
    -0.49
     ThemeData
    -0.48
     ""],
    -0.47
     USP
    -0.47
    POSITIVE LOGITS
     Slightly
    0.59
    EINVAL
    0.57
     makl
    0.56
     slightly
    0.55
    databind
    0.51
    tole
    0.50
    levé
    0.48
     Somewhat
    0.48
    낀
    0.47
     Vito
    0.46
    Activations Density 0.001%

    No Known Activations