© 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. 4-CLT-HP
    7. 3405
    Prev
    Next
    INDEX
    Explanations

    excerpts

    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
    Personendaten
    -0.61
     autorytatywna
    -0.58
    vency
    -0.57
    windowFixed
    -0.54
    Datuak
    -0.54
    ValueStyle
    -0.54
    udges
    -0.53
    De
    -0.53
    SourceChecksum
    -0.53
    bute
    -0.52
    POSITIVE LOGITS
    ">//
    0.54
    IntoConstraints
    0.52
    Personensuche
    0.51
    AddTagHelper
    0.50
     Cycl
    0.47
    )="
    0.46
    TagHelpers
    0.46
    crivez
    0.45
    ArrowToggle
    0.45
     whither
    0.44
    Activations Density 0.007%

    No Known Activations