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. 0-CLT-HP
    4. 40807
    Prev
    Next
    INDEX
    Explanations

    impl

    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
    impl
    -1.16
    Impl
    -0.93
     PDP
    -0.75
    GOTREF
    -0.63
    PDP
    -0.61
    langer
    -0.59
    ees
    -0.56
    saraba
    -0.55
     LCCN
    -0.55
     paramInt
    -0.55
    POSITIVE LOGITS
     صوتيه
    0.63
     متعلقه
    0.56
     مشين
    0.55
    audiovisuel
    0.54
    ant
    0.52
    ArrowToggle
    0.51
    WithMany
    0.47
    vency
    0.45
    ta
    0.44
    fin
    0.44
    Activations Density 0.865%

    No Known Activations