© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 41396
    Prev
    Next
    INDEX
    Explanations

    tious

    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
    ########.
    -0.83
    collections
    -0.69
    CLUD
    -0.67
     collections
    -0.65
     Devlin
    -0.65
     Troubles
    -0.61
    waters
    -0.59
    berts
    -0.58
    akin
    -0.58
    ppes
    -0.57
    POSITIVE LOGITS
     Suomessa
    0.60
    cèse
    0.57
    ⓧ
    0.56
    FXML
    0.56
     sostanza
    0.54
     brasileiros
    0.53
     vastaan
    0.53
     menengah
    0.53
    BindingResult
    0.53
     født
    0.52
    Activations Density 0.053%

    No Known Activations