© 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. 5-CLT-HP
    4. 2037
    Prev
    Next
    INDEX
    Explanations

    memory/past events

    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
     to
    -0.50
    irsi
    -0.45
    rogen
    -0.42
    ρό
    -0.42
    key
    -0.42
    antMatchers
    -0.42
    gero
    -0.41
    addComponent
    -0.41
    ump
    -0.40
    Архівовано
    -0.40
    POSITIVE LOGITS
    Extinguishing
    0.74
     InputDecoration
    0.72
    LookAnd
    0.67
     Reverso
    0.66
    ItemBackground
    0.66
     withdrawing
    0.63
    IUrlHelper
    0.62
    disposing
    0.61
     picking
    0.60
     disambiguazione
    0.60
    Activations Density 0.001%

    No Known Activations