© 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. 0-CLT-HP
    7. 94250
    Prev
    Next
    INDEX
    Explanations

    based

    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
    \{\\
    -0.86
     فريبيس
    -0.77
    })));
    -0.76
     vostri
    -0.76
     ());
    -0.72
     صوتيه
    -0.71
     gevolg
    -0.70
    UrlResolution
    -0.69
    Билгалдахарш
    -0.66
     parachoque
    -0.65
    POSITIVE LOGITS
     the
    0.54
     this
    0.48
     like
    0.46
     then
    0.46
     تضيفلها
    0.46
     not
    0.45
     everything
    0.44
     below
    0.44
     work
    0.43
     Vương
    0.43
    Activations Density 0.058%

    No Known Activations