© 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. 0-CLT-HP
    7. 95242
    Prev
    Next
    INDEX
    Explanations

    Original

    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
    s
    -0.68
    es
    -0.65
    a
    -0.63
     Original
    -0.60
    e
    -0.58
    er
    -0.57
     Current
    -0.56
    inoma
    -0.55
    ی
    -0.54
    o
    -0.53
    POSITIVE LOGITS
     Roskov
    1.02
    LookAnd
    1.00
     AssemblyProduct
    0.98
    StoryboardSegue
    0.98
    ьаж
    0.96
    IUrlHelper
    0.92
     AttributeSet
    0.90
    SBATCH
    0.90
     ModelExpression
    0.89
     betweenstory
    0.89
    Activations Density 0.196%

    No Known Activations