© 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. 5155
    Prev
    Next
    INDEX
    Explanations

    differences

    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
    DockStyle
    -0.51
    gner
    -0.48
    Foreword
    -0.43
     numerus
    -0.42
     satellites
    -0.42
    endcsname
    -0.42
    icrous
    -0.42
     Chancellor
    -0.41
    TECHNOLOGY
    -0.41
    secre
    -0.40
    POSITIVE LOGITS
     nahilalakip
    0.90
     دیکھیے
    0.69
    webElementXpaths
    0.68
     beginnetje
    0.67
    CppMethod
    0.61
     ThemeData
    0.61
    abetes
    0.61
     وتسجيلات
    0.59
     ddelweddau
    0.59
     clín
    0.59
    Activations Density 0.003%

    No Known Activations