© 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. 3532
    Prev
    Next
    INDEX
    Explanations

    to

    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
    esu
    -0.51
    eap
    -0.50
     Kokos
    -0.47
    anglès
    -0.47
     CreateTagHelper
    -0.47
    quias
    -0.46
     kuri
    -0.46
     Roskov
    -0.45
    PubMed
    -0.45
     لينك
    -0.45
    POSITIVE LOGITS
    titleMargin
    0.70
     AssemblyProduct
    0.64
    argout
    0.63
     ModelRenderer
    0.63
     محفوظة
    0.59
    ódó
    0.53
    AutoField
    0.52
    Numerology
    0.52
    Parcelize
    0.52
     Anſ
    0.52
    Activations Density 0.029%

    No Known Activations