© 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
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 92726
    Prev
    Next
    INDEX
    Explanations

    ticks

    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
    ticks
    -1.65
    essional
    -0.72
    tona
    -0.61
    Ticks
    -0.60
     EDT
    -0.53
     BnF
    -0.52
    +#+#
    -0.47
    Diámetro
    -0.47
    ientôt
    -0.44
    Gruß
    -0.43
    POSITIVE LOGITS
    MigrationBuilder
    0.66
    >//
    0.59
    hoodie
    0.58
    WriteAttribute
    0.56
    Tikang
    0.56
    RenderAtEndOf
    0.54
    cupa
    0.54
     Noida
    0.53
    setVerticalGroup
    0.52
     nought
    0.52
    Activations Density 0.079%

    No Known Activations