© 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. 20-CLT-HP
    7. 77392
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act-logits · 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
    enumi
    -0.82
    Personendaten
    -0.74
    ########.
    -0.73
    WriteAttribute
    -0.63
    Datuak
    -0.62
    BrowserModule
    -0.60
     <>",
    -0.60
     GenerationType
    -0.60
     onAnimation
    -0.59
    קישורים
    -0.59
    POSITIVE LOGITS
     o
    0.60
    Hej
    0.56
     caza
    0.52
     Mam
    0.50
     governor
    0.49
     régl
    0.48
     vi
    0.47
    oderm
    0.47
    存于互联网档案馆
    0.47
     Wi
    0.47
    Activations Density 0.000%

    No Known Activations