© 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. 0-CLT-HP
    7. 95481
    Prev
    Next
    INDEX
    Explanations

    based

    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
    based
    -1.51
    Based
    -1.51
     based
    -1.47
     Based
    -1.36
     BASED
    -1.23
    BASED
    -1.07
     baseado
    -1.05
     themselves
    -1.00
     basada
    -0.96
     basado
    -0.95
    POSITIVE LOGITS
     on
    0.86
    Filmographie
    0.82
    CodeAttribute
    0.80
    Filmography
    0.77
     estekak
    0.73
    setVerticalGroup
    0.71
     off
    0.69
    ConstraintMaker
    0.65
    WithMany
    0.64
     références
    0.63
    Activations Density 0.068%

    No Known Activations