© 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. 5-CLT-HP
    7. 93822
    Prev
    Next
    INDEX
    Explanations

    me

    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
     发表于
    -0.60
    fromnode
    -0.55
    ProgressHUD
    -0.49
    Ibid
    -0.49
     JpaRepository
    -0.45
     مشين
    -0.45
    matig
    -0.45
     Réponses
    -0.45
    tesi
    -0.44
    ᅠ
    -0.44
    POSITIVE LOGITS
     what
    0.59
    fjspx
    0.59
     why
    0.57
    pensive
    0.55
     travaillons
    0.54
    nissen
    0.53
     Sarmiento
    0.53
    ierungen
    0.52
    nativeElement
    0.52
    хьтан
    0.51
    Activations Density 0.018%

    No Known Activations