© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 93020
    Prev
    Next
    INDEX
    Explanations

    2

    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
     same
    -0.43
    .
    -0.42
    pe
    -0.42
    netbeans
    -0.40
     rame
    -0.39
    </strong>
    -0.39
     культуры
    -0.38
     background
    -0.38
    mame
    -0.38
     doble
    -0.38
    POSITIVE LOGITS
    aarrggbb
    1.11
    Tikang
    0.92
    MessageOf
    0.78
     ſtate
    0.76
    Datuak
    0.75
    windowFixed
    0.73
     autorytatywna
    0.73
    ########.
    0.72
    енча
    0.72
     Taktlose
    0.71
    Activations Density 0.001%

    No Known Activations