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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 22-CLT-HP
    4. 74576
    Prev
    Next
    INDEX
    Explanations

    other languages

    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
     Juárez
    -0.56
    CopyWith
    -0.55
     Fry
    -0.54
    fillType
    -0.54
    MLLoader
    -0.53
    fry
    -0.53
     ThemeData
    -0.53
     Calais
    -0.52
    tagHelperRunner
    -0.52
     érde
    -0.51
    POSITIVE LOGITS
     gynhyrchwyd
    0.68
     дописавши
    0.57
    IVEREF
    0.55
     '\\;'
    0.53
     المعيارى
    0.48
    |}{}
    0.46
    AnchorStyles
    0.45
    setViewportView
    0.44
    /**
    0.44
    Autoritní
    0.44
    Activations Density 0.026%

    No Known Activations