© 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. 4829
    Prev
    Next
    INDEX
    Explanations

    Media/editing/censorship

    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
    sira
    -0.45
    unmodifiable
    -0.43
    ường
    -0.42
     Trink
    -0.42
     Regist
    -0.41
    qua
    -0.41
    yra
    -0.41
    emark
    -0.41
    mspace
    -0.41
     gentes
    -0.41
    POSITIVE LOGITS
     ویکی‌پدیا
    0.71
     الرياضيه
    0.68
     esternos
    0.63
    JNIEnv
    0.61
     AttributeSet
    0.60
     Normdatei
    0.57
    Spoljašnje
    0.57
    manteau
    0.56
    Personensuche
    0.56
     referenties
    0.56
    Activations Density 0.014%

    No Known Activations