© 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. 4-CLT-HP
    7. 1402
    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
    -0.49
    Sure
    -0.47
    vasti
    -0.45
    ProgressHUD
    -0.45
     ideje
    -0.43
    unque
    -0.42
    stånd
    -0.42
     nära
    -0.42
     though
    -0.42
     sicura
    -0.41
    POSITIVE LOGITS
     NSCoder
    0.77
     متعلقه
    0.66
     magasiner
    0.64
     fortn
    0.63
    ✨:
    0.63
     صوتيه
    0.63
    Hentet
    0.63
     Allein
    0.60
    olol
    0.59
     تضيفلها
    0.59
    Activations Density 0.003%

    No Known Activations