© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 96624
    Prev
    Next
    INDEX
    Explanations

    charts and visual elements

    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
    IUrlHelper
    -0.63
    раздо
    -0.63
    })));
    -0.60
     ModelExpression
    -0.44
    "]}
    -0.42
    期刊论文
    -0.42
    ίδι
    -0.41
    richTextPanel
    -0.41
    Somehow
    -0.41
     Somehow
    -0.40
    POSITIVE LOGITS
     FontWeight
    0.63
    ScopeManager
    0.59
    webElement
    0.55
     AppCompat
    0.54
    TextSpan
    0.53
     Vikipedi
    0.53
     BoxDecoration
    0.52
    OrBuilder
    0.52
     ThemeData
    0.51
     textColor
    0.51
    Activations Density 0.004%

    No Known Activations