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. 73967
    Prev
    Next
    INDEX
    Explanations

    Technical references

    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
     referenties
    -0.71
     purpoſe
    -0.65
     fhew
    -0.63
     Efq
    -0.61
    
    -0.61
     myſelf
    -0.59
     Baillargeon
    -0.59
     Jefus
    -0.58
     fhall
    -0.57
     AssemblyVersion
    -0.57
    POSITIVE LOGITS
     for
    0.47
    çalves
    0.47
     demografica
    0.47
     موجود
    0.43
     gu
    0.42
    ỏa
    0.42
     data
    0.42
    cticut
    0.42
    adav
    0.42
     nor
    0.41
    Activations Density 0.003%

    No Known Activations