© 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. 95025
    Prev
    Next
    INDEX
    Explanations

    Main

    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
    otherwise
    -0.62
     otherwise
    -0.60
     cherchez
    -0.55
    ,
    -0.54
     ogóle
    -0.54
     altrimenti
    -0.53
     and
    -0.50
     Alternatively
    -0.50
     alternatively
    -0.50
    ypeł
    -0.49
    POSITIVE LOGITS
    ContentAsync
    0.65
     AssemblyTitle
    0.55
    iastes
    0.55
    WebElementEntity
    0.55
    
    0.52
    dafx
    0.52
    ]<<"
    0.52
     OnTrigger
    0.52
    parsedMessage
    0.51
    
    0.50
    Activations Density 0.000%

    No Known Activations