© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 93229
    Prev
    Next
    INDEX
    Explanations

    do/does

    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
    NgModule
    -0.61
     NgModule
    -0.60
    antMatchers
    -0.58
    RUnlock
    -0.56
    \{\\
    -0.56
     ویکی‌پدی
    -0.54
     adjustment
    -0.52
    UnsafeEnabled
    -0.51
    ByPrimaryKey
    -0.50
    thard
    -0.50
    POSITIVE LOGITS
     however
    0.57
    AndEndTag
    0.56
    CppMethod
    0.56
    wnież
    0.52
     vVar
    0.51
    batore
    0.51
    Tembelea
    0.51
     Però
    0.50
     utafitiHapana
    0.49
     so
    0.48
    Activations Density 0.001%

    No Known Activations