© 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. 0-CLT-HP
    4. 90951
    Prev
    Next
    INDEX
    Explanations

    rearrangements/assisted processes

    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
     avoient
    -0.77
     auroit
    -0.75
     marquées
    -0.72
     overcoming
    -0.72
     Houſe
    -0.71
     spéciales
    -0.71
     vandens
    -0.71
     Assisted
    -0.70
     feroit
    -0.70
     mélang
    -0.69
    POSITIVE LOGITS
    webElementXpaths
    0.68
    tagHelperRunner
    0.67
     صوتيه
    0.59
    elemField
    0.57
     pas
    0.57
    ]));
    
    0.57
     Fre
    0.55
    Искәрмәләр
    0.54
    ]))
    
    0.54
    щика
    0.52
    Activations Density 0.065%

    No Known Activations