© 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
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 12216
    Prev
    Next
    INDEX
    Explanations

    R

    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
    CastException
    -0.66
     dislocations
    -0.65
     Hampden
    -0.60
     hibern
    -0.58
     glaucoma
    -0.58
    Personendaten
    -0.56
     Samaria
    -0.56
     hippo
    -0.56
     hibernation
    -0.54
     gills
    -0.54
    POSITIVE LOGITS
     kaynağından
    0.59
    évaluateur
    0.57
     saites
    0.54
    alised
    0.53
    ised
    0.52
    LEncoder
    0.48
    ising
    0.47
     Всё
    0.46
    脚注の使い方
    0.46
     semula
    0.46
    Activations Density 0.014%

    No Known Activations