© 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. 5704
    Prev
    Next
    INDEX
    Explanations

    P

    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
    ########.
    -0.69
     незавершена
    -0.66
    eseorang
    -0.61
     ويكيپيديا
    -0.55
    PreferredItem
    -0.53
     onCreateView
    -0.53
    Rüyada
    -0.52
     hinweg
    -0.52
     betweenstory
    -0.50
    󠁴
    -0.50
    POSITIVE LOGITS
     onAnimation
    0.55
    Kn
    0.53
    uParam
    0.51
    pecha
    0.51
    NS
    0.49
    errHandler
    0.48
     caveats
    0.48
    有所
    0.48
    /
    0.47
    NG
    0.47
    Activations Density 0.002%

    No Known Activations