Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 73995
    Prev
    Next
    INDEX
    Explanations

    technical/informational content

    np_max-act-logits · 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
    -0.82
     AssemblyVersion
    -0.59
    tagHelperRunner
    -0.59
    PerformLayout
    -0.58
     bearings
    -0.57
    BagConstraints
    -0.56
     Bearings
    -0.55
    󠁢
    -0.55
    xffffff
    -0.55
     SafeMath
    -0.55
    POSITIVE LOGITS
    RegressionTest
    0.64
    كويكب
    0.56
    InitVars
    0.50
    IonicModule
    0.41
    inter
    0.40
    utto
    0.40
    INTER
    0.40
    StoreMessageInfo
    0.40
    uc
    0.40
     inter
    0.40
    Activations Density 0.001%

    No Known Activations