© 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. 5-CLT-HP
    7. 91908
    Prev
    Next
    INDEX
    Explanations

    the

    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
    expandindo
    -0.64
     GenerationType
    -0.59
     myself
    -0.57
     pageContext
    -0.48
     gainera
    -0.47
    Solución
    -0.46
     smtplib
    -0.45
     Ressources
    -0.44
    BeginContext
    -0.44
     aapt
    -0.42
    POSITIVE LOGITS
    ientôt
    0.68
    MeasureSpec
    0.66
    AccessorTable
    0.65
     AssemblyTitle
    0.63
    djangoproject
    0.63
    guenos
    0.63
    SpringBootTest
    0.59
    ituary
    0.58
    Portail
    0.58
    Obrázky
    0.58
    Activations Density 0.000%

    No Known Activations