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. 74177
    Prev
    Next
    INDEX
    Explanations

    Re

    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
     considérons
    -0.71
     AssemblyTitle
    -0.61
    saraba
    -0.56
     nodded
    -0.50
    oa̍t
    -0.50
     дописавши
    -0.50
    verwijspagina
    -0.49
    CrossRef
    -0.49
    bibitem
    -0.49
    -------------</
    -0.48
    POSITIVE LOGITS
    bbene
    0.55
    closedir
    0.47
    ροι
    0.45
    ABN
    0.45
     lenker
    0.45
    GOTREF
    0.45
    GREATER
    0.43
    megen
    0.42
    ელი
    0.42
    żesz
    0.41
    Activations Density 0.002%

    No Known Activations