© 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. 0-CLT-HP
    7. 97733
    Prev
    Next
    INDEX
    Explanations

    lative

    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
    Personendaten
    -1.30
     resourceCulture
    -1.10
    SharedDtor
    -1.08
    ⓧ
    -1.07
    帖最后由
    -1.06
    Autoritní
    -1.05
     Paglinawan
    -1.04
     CreateTagHelper
    -1.02
     raiſ
    -1.02
    rungsseite
    -1.02
    POSITIVE LOGITS
    sim
    0.55
    si
    0.52
    da
    0.50
    ni
    0.47
     ber
    0.46
    ny
    0.46
    mor
    0.45
    ser
    0.44
    lat
    0.43
    nt
    0.43
    Activations Density 0.045%

    No Known Activations