© 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. 1762
    Prev
    Next
    INDEX
    Explanations

    question

    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
    question
    -0.51
    Question
    -0.50
    putchar
    -0.48
    astype
    -0.48
     svå
    -0.45
    hiz
    -0.44
     vanske
    -0.43
    ژاد
    -0.42
     Teams
    -0.39
    avyzd
    -0.39
    POSITIVE LOGITS
    ChildIndex
    0.87
    elry
    0.82
    exitRule
    0.82
    protoimpl
    0.79
    ########.
    0.78
    adecimal
    0.71
    age
    0.69
     Чита
    0.69
     SwitchCompat
    0.69
    afficheront
    0.68
    Activations Density 0.326%

    No Known Activations