© 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. 5985
    Prev
    Next
    INDEX
    Explanations

    make sets

    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
    IsContent
    -0.66
    SupportActionBar
    -0.63
    ГЛА
    -0.53
     SafeMath
    -0.52
    IZONT
    -0.51
    Fonti
    -0.50
    Kilder
    -0.49
    KEYCODE
    -0.48
    AnchorStyles
    -0.47
     doInBackground
    -0.47
    POSITIVE LOGITS
     me
    0.70
     you
    0.58
     a
    0.54
    RegistryLite
    0.54
     us
    0.54
     our
    0.53
    tså
    0.53
     this
    0.52
     civilizations
    0.51
     Roskov
    0.50
    Activations Density 0.002%

    No Known Activations