© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 72118
    Prev
    Next
    INDEX
    Explanations

    code and technical documentation

    np_max-act-logits · 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
    PerformLayout
    -0.65
     Autorizaciones
    -0.60
    Lamar
    -0.57
     שוליים
    -0.56
    ⓧ
    -0.54
    thâu
    -0.54
    noopener
    -0.53
    UrlResolution
    -0.52
     Roskov
    -0.52
     Lamar
    -0.51
    POSITIVE LOGITS
     StatefulWidget
    0.55
     habl
    0.47
    nonatomic
    0.47
    tanleria
    0.47
    cues
    0.46
     Kró
    0.45
     StatelessWidget
    0.45
     kg
    0.44
     Audiodateien
    0.44
    KING
    0.44
    Activations Density 0.001%

    No Known Activations