© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 2304
    Prev
    Next
    INDEX
    Explanations

    steps or numbering

    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
     esperienze
    -0.59
     termica
    -0.58
     récente
    -0.57
     nationaux
    -0.56
     nødven
    -0.56
    TestingModule
    -0.56
     demurrer
    -0.56
     păr
    -0.55
     esterna
    -0.54
     applicazioni
    -0.54
    POSITIVE LOGITS
    hnia
    0.51
     мәкал
    0.51
     Baillargeon
    0.51
    AnchorStyles
    0.50
     AssemblyCulture
    0.50
     برانيه
    0.48
     Hacker
    0.45
     HasFactory
    0.45
     AppCompatTheme
    0.44
     transfieras
    0.44
    Activations Density 0.001%

    No Known Activations