© 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. 1-CLT-HP
    7. 527
    Prev
    Next
    INDEX
    Explanations

    tests

    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
     agility
    -1.04
     Agility
    -0.86
    Agility
    -0.74
     agile
    -0.55
    logist
    -0.51
    ValueStyle
    -0.50
    agile
    -0.50
    nium
    -0.46
    iella
    -0.45
    CHAS
    -0.45
    POSITIVE LOGITS
    __':
    0.68
    saraba
    0.66
     tartalomajánló
    0.65
    UrlResolution
    0.64
     Kens
    0.64
     lenker
    0.63
     BorderSide
    0.60
     EconPapers
    0.60
     ModelRenderer
    0.59
    dhury
    0.59
    Activations Density 0.164%

    No Known Activations