© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 46294
    Prev
    Next
    INDEX
    Explanations

    speed/velocity

    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
    tagHelperRunner
    -0.61
     protoimpl
    -0.61
    webElementXpaths
    -0.61
    StoryboardSegue
    -0.58
    ViewFeatures
    -0.55
    OGND
    -0.52
     speed
    -0.52
    ReusableCell
    -0.51
     lenker
    -0.50
    andExpect
    -0.49
    POSITIVE LOGITS
    ніципа
    0.63
     GTO
    0.61
    ChildScrollView
    0.61
    ietal
    0.56
     firebaseConfig
    0.55
     CURIAM
    0.54
    <bos>
    0.53
    ciaio
    0.52
    æld
    0.52
     Kirchner
    0.52
    Activations Density 0.128%

    No Known Activations