Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 74248
    Prev
    Next
    INDEX
    Explanations

    Technical document context

    np_max-act-logits · 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
    ftagPool
    -0.80
     houſe
    -0.80
     виправивши
    -0.77
     NSCoder
    -0.76
     متعلقه
    -0.69
     Houſe
    -0.67
    posedge
    -0.66
     bezeichneter
    -0.66
     تضيفلها
    -0.65
    
    -0.65
    POSITIVE LOGITS
    ://$
    0.43
     [*]
    0.42
    olas
    0.42
     Michael
    0.41
     $
    0.39
     session
    0.38
    angi
    0.37
     Ser
    0.36
    ná
    0.35
     ang
    0.34
    Activations Density 0.000%

    No Known Activations