© 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. 4-CLT-HP
    7. 333
    Prev
    Next
    INDEX
    Explanations

    site

    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
    ΕΣ
    -0.56
    tawesome
    -0.53
    ejs
    -0.50
     interested
    -0.47
     Solicitors
    -0.47
    SCOP
    -0.47
     Remedies
    -0.47
    tives
    -0.47
     Pu
    -0.46
    Pu
    -0.46
    POSITIVE LOGITS
    PageContext
    0.67
    MENAFN
    0.65
    ScopeManager
    0.61
    awtextra
    0.59
    ValueStyle
    0.58
    BufferException
    0.56
     DialogInterface
    0.56
     فريبيس
    0.56
    \{\\
    0.56
    DockStyle
    0.56
    Activations Density 0.001%

    No Known Activations