© 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. 92730
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
     and
    -0.52
    :✨
    -0.43
     wie
    -0.43
     de
    -0.41
    тельно
    -0.40
     communiquez
    -0.38
     fit
    -0.37
     or
    -0.36
     pan
    -0.36
    </sup>
    -0.36
    POSITIVE LOGITS
     Efq
    0.96
     ſche
    0.92
     ſtate
    0.82
     ſta
    0.82
     wikipagina
    0.81
     abſ
    0.79
     purpoſe
    0.79
     alamu
    0.79
     raiſ
    0.79
     ſou
    0.79
    Activations Density 0.001%

    No Known Activations