© 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
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 4534
    Prev
    Next
    INDEX
    Explanations

    Code snippets

    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
    DockStyle
    -0.76
     calendriers
    -0.66
    IUrlHelper
    -0.65
     дописавши
    -0.65
    :✨
    -0.65
     Numerade
    -0.61
     reserve
    -0.59
     NSCoder
    -0.59
    UnknownFields
    -0.59
    GIVEREF
    -0.58
    POSITIVE LOGITS
    Према
    0.42
     planète
    0.42
     dör
    0.42
     consultato
    0.40
     Préférences
    0.40
    fä
    0.38
    Referências
    0.36
     föruts
    0.36
    倫
    0.35
     ses
    0.35
    Activations Density 0.067%

    No Known Activations