© 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. 1-CLT-HP
    7. 9703
    Prev
    Next
    INDEX
    Explanations

    above

    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
     Griffiths
    -0.48
    TabIndex
    -0.47
    uri
    -0.47
    umlu
    -0.45
    idere
    -0.45
     Jackson
    -0.40
     cracking
    -0.40
     дирек
    -0.40
    الی
    -0.40
    ter
    -0.39
    POSITIVE LOGITS
    expandindo
    0.76
    </tfoot>
    0.73
    RectangleBorder
    0.67
    ècie
    0.65
     مشين
    0.65
     محفوظة
    0.65
     AssemblyProduct
    0.65
     متعلقه
    0.64
    GEBURTSDATUM
    0.64
    suits
    0.63
    Activations Density 0.016%

    No Known Activations