© 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. 91144
    Prev
    Next
    INDEX
    Explanations

    life and death situations

    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
     CreateTagHelper
    -0.59
     Neat
    -0.58
    adpleegd
    -0.54
     Efq
    -0.52
    zido
    -0.52
    indd
    -0.52
    )}</
    -0.52
     vícti
    -0.50
    娩
    -0.49
     insuffisamment
    -0.49
    POSITIVE LOGITS
    IsContent
    0.75
    TRAILING
    0.71
    StructEnd
    0.67
    didSet
    0.66
    CreateModel
    0.60
     Référence
    0.60
    dataclass
    0.56
    titian
    0.56
    elemField
    0.55
    forKey
    0.54
    Activations Density 0.001%

    No Known Activations