© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 41202
    Prev
    Next
    INDEX
    Explanations

    GS

    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
    orsch
    -0.74
    hetamine
    -0.71
     GS
    -0.68
    relli
    -0.57
     ***!
    -0.51
     InputDecoration
    -0.51
    ########.
    -0.51
     fieldNum
    -0.50
    "?>
    -0.50
    ernsey
    -0.50
    POSITIVE LOGITS
    WebVitals
    0.70
    IVEREF
    0.70
    SBATCH
    0.65
    tonsoft
    0.62
    WithIOException
    0.57
     sûre
    0.56
    saraba
    0.56
     WaitForSeconds
    0.54
     lenker
    0.53
    /**
    0.53
    Activations Density 1.551%

    No Known Activations