© 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. 5-CLT-HP
    7. 95045
    Prev
    Next
    INDEX
    Explanations

    many

    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
    makeConstraints
    -0.71
     estekak
    -0.67
     ligiloj
    -0.66
    ReusableCell
    -0.65
     Biôgrafia
    -0.63
     Roskov
    -0.62
    Personensuche
    -0.60
     AssemblyCulture
    -0.59
    ConstraintMaker
    -0.58
    GOTREF
    -0.57
    POSITIVE LOGITS
     of
    1.34
     the
    0.57
     aspects
    0.56
     của
    0.54
    ของ
    0.52
     tohoto
    0.52
     current
    0.50
     ofthe
    0.50
     highlights
    0.50
     našich
    0.49
    Activations Density 0.005%

    No Known Activations