© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 987
    Prev
    Next
    INDEX
    Explanations

    technical/academic writing

    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
    ientôt
    -0.71
    tagHelperRunner
    -0.71
     autorytatywna
    -0.64
    eseorang
    -0.60
    Хьажоргаш
    -0.59
    !("{}",
    -0.59
     Chriftian
    -0.59
    entibus
    -0.59
    ^(@)
    -0.58
     invokingState
    -0.58
    POSITIVE LOGITS
    persistent
    0.50
     pere
    0.48
     sockaddr
    0.46
    pr
    0.44
    صرية
    0.43
    uma
    0.43
    PER
    0.42
    Precautionary
    0.42
    Pru
    0.42
     betweenstory
    0.41
    Activations Density 0.003%

    No Known Activations