© 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. 6031
    Prev
    Next
    INDEX
    Explanations

    programming

    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
    :✨
    -0.60
    perity
    -0.56
    offsetof
    -0.56
     MenuView
    -0.56
    PONENTS
    -0.55
    ecuted
    -0.53
    öbb
    -0.52
    bitol
    -0.52
     synthase
    -0.51
    setViewportView
    -0.51
    POSITIVE LOGITS
    存于互联网档案馆
    0.71
    }();
    0.65
    ieteur
    0.57
     présidenti
    0.53
    verwijspagina
    0.52
    Бахар
    0.50
    DockStyle
    0.49
    AutoresizingMask
    0.48
     LUMP
    0.47
    (!__
    0.47
    Activations Density 0.036%

    No Known Activations