© 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. 97085
    Prev
    Next
    INDEX
    Explanations

    limiting words

    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
    ValueStyle
    -0.56
     समीक्षाएं
    -0.53
    ✨:
    -0.52
     AppCompatTheme
    -0.51
     lenker
    -0.50
    ientí
    -0.49
    DeleteBehavior
    -0.49
     getPage
    -0.48
    appe
    -0.48
     ostavi
    -0.48
    POSITIVE LOGITS
     snippetHide
    0.67
    drawiam
    0.57
    <bos>
    0.49
     seeking
    0.49
     going
    0.48
    RegressionTest
    0.47
    thesis
    0.47
    ApiProperty
    0.46
     defending
    0.46
     practising
    0.46
    Activations Density 0.005%

    No Known Activations