© 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. 4-CLT-HP
    7. 647
    Prev
    Next
    INDEX
    Explanations

    and

    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
    InputBorder
    -0.55
     Pública
    -0.52
    ToBounds
    -0.52
     NSCoder
    -0.51
    ImageContext
    -0.50
    thâu
    -0.49
    roek
    -0.48
     Hebrew
    -0.47
    InvalidProtocol
    -0.47
    Хьажоргаш
    -0.46
    POSITIVE LOGITS
     Bioaccumulative
    0.57
    ⤹
    0.55
     فريبيس
    0.52
    Кры
    0.51
     Gennaio
    0.50
    ägg
    0.50
     صوتيه
    0.50
     câte
    0.50
    opedia
    0.49
    ceptar
    0.49
    Activations Density 0.001%

    No Known Activations