© 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. 5-CLT-HP
    7. 92541
    Prev
    Next
    INDEX
    Explanations

    code/file paths

    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
     Alhambra
    -0.91
    +#+
    -0.63
     вікі
    -0.59
     Roskov
    -0.59
    esez
    -0.58
    ifornie
    -0.57
     considérons
    -0.57
     تضيفلها
    -0.55
    onomy
    -0.54
    ActionCreators
    -0.54
    POSITIVE LOGITS
    richTextPanel
    0.60
    IonicModule
    0.52
     يتيمه
    0.51
     BoxDecoration
    0.50
    djangoproject
    0.48
    RRect
    0.45
    SequentialGroup
    0.45
    Serde
    0.44
     BoxFit
    0.44
    haikusbot
    0.43
    Activations Density 0.011%

    No Known Activations