© 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. 0-CLT-HP
    7. 43373
    Prev
    Next
    INDEX
    Explanations

    technical 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
    ंदीखरीदारी
    -1.05
    Personendaten
    -0.87
    ագրություններ
    -0.87
     Roskov
    -0.81
    DockStyle
    -0.81
     esternos
    -0.80
    webElementXpaths
    -0.79
    Autoritní
    -0.79
     demand
    -0.79
     Signalez
    -0.79
    POSITIVE LOGITS
     for
    0.74
    for
    0.57
     françaises
    0.57
     artistico
    0.54
     juridiques
    0.52
    http
    0.51
    .
    0.51
     russes
    0.50
    sy
    0.50
    todas
    0.50
    Activations Density 0.014%

    No Known Activations