© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 91195
    Prev
    Next
    INDEX
    Explanations

    arrival or movement

    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
    ="@+
    -0.63
    Rüyada
    -0.60
     الحره
    -0.56
     HasFactory
    -0.54
    UrlResolution
    -0.53
     필
    -0.52
     ویکی‌پدیا
    -0.52
     encomp
    -0.52
     understanding
    -0.52
    erle
    -0.52
    POSITIVE LOGITS
     muualla
    0.52
    \{\\
    0.51
    CloseOperation
    0.49
     GetEnumerator
    0.49
    withIdentifier
    0.49
    ProgressHUD
    0.47
    Componentes
    0.46
    umumkan
    0.45
    عات
    0.44
     hoje
    0.44
    Activations Density 0.001%

    No Known Activations