© 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. 1-CLT-HP
    7. 8916
    Prev
    Next
    INDEX
    Explanations

    time units

    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
     years
    -0.56
    OPLE
    -0.52
    licken
    -0.51
     niên
    -0.50
    的身
    -0.50
    WEET
    -0.47
     old
    -0.47
     mature
    -0.47
     plausible
    -0.46
    多年
    -0.46
    POSITIVE LOGITS
    ########.
    0.71
    IntoConstraints
    0.65
    #+#
    0.63
    IndentedString
    0.62
    ölkerung
    0.61
    ExtendWith
    0.61
    DockStyle
    0.61
    Kariera
    0.60
    ViewFeatures
    0.59
    prefixer
    0.57
    Activations Density 0.289%

    No Known Activations