© 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. 0-CLT-HP
    7. 40047
    Prev
    Next
    INDEX
    Explanations

    relaxation

    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
    IntoConstraints
    -0.75
     vœux
    -0.75
     ErrIntOverflow
    -0.71
    WebElementEntity
    -0.67
     atenta
    -0.66
    ########.
    -0.66
    ValueStyle
    -0.66
    fjspx
    -0.65
    AddTagHelper
    -0.65
     Biôgrafia
    -0.64
    POSITIVE LOGITS
    ists
    0.50
    ΗΣ
    0.47
    sic
    0.46
    ductory
    0.46
    bkz
    0.46
    ship
    0.44
    typeid
    0.43
     techniques
    0.43
     guess
    0.43
    IMENTS
    0.43
    Activations Density 0.643%

    No Known Activations