© 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. 4471
    Prev
    Next
    INDEX
    Explanations

    torn

    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
    fjspx
    -0.71
    Geplaatst
    -0.70
    terase
    -0.64
    jdons
    -0.62
    期刊论文
    -0.59
     esternos
    -0.59
    OpenHelper
    -0.58
     发表于
    -0.58
    الحياه
    -0.57
    queous
    -0.56
    POSITIVE LOGITS
     off
    0.45
     selv
    0.44
    multer
    0.43
    setViewportView
    0.41
     leop
    0.41
    Ladd
    0.41
    atsun
    0.40
    ita
    0.40
    bof
    0.39
     wider
    0.39
    Activations Density 0.001%

    No Known Activations