© 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. 93904
    Prev
    Next
    INDEX
    Explanations

    emblem

    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
     spent
    -0.88
     Spent
    -0.86
     paid
    -0.84
    spent
    -0.82
    paid
    -0.79
     wasted
    -0.76
     pagado
    -0.70
     Paid
    -0.66
    Paid
    -0.66
     Shovel
    -0.63
    POSITIVE LOGITS
    Билгалдахарш
    0.82
    fjspx
    0.62
     الرياضيه
    0.60
     OMITBAD
    0.60
     Normdatei
    0.57
    ThemeOverlay
    0.55
    PostInfinity
    0.54
    AndEndTag
    0.54
     puissiez
    0.53
    衛門
    0.50
    Activations Density 0.036%

    No Known Activations