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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 534
    Prev
    Next
    INDEX
    Explanations

    freedom

    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
    ?,?,
    -0.50
    BrowserModule
    -0.46
     defStyleAttr
    -0.45
     chup
    -0.45
    XtraEditors
    -0.43
     quen
    -0.43
    ivir
    -0.43
    pulo
    -0.42
    Palmarès
    -0.41
    InputTagHelper
    -0.41
    POSITIVE LOGITS
    expandindo
    0.78
     Paglinawan
    0.73
    KommentareTeilen
    0.70
    Tikang
    0.66
     Wikimedijinoj
    0.63
     pinulongan
    0.63
     quelconque
    0.63
    seamnă
    0.60
     policiales
    0.59
    ⓧ
    0.58
    Activations Density 0.009%

    No Known Activations