© 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. 91257
    Prev
    Next
    INDEX
    Explanations

    shown

    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
     tartalomajánló
    -0.74
    StructEnd
    -0.72
    EndContext
    -0.69
     EconPapers
    -0.69
    abestanden
    -0.60
     ligiloj
    -0.60
     viewDidLoad
    -0.59
    InjectAttribute
    -0.59
     GenerationType
    -0.59
    invokeLater
    -0.59
    POSITIVE LOGITS
    previously
    0.49
     previously
    0.46
    further
    0.45
    ագրություններ
    0.45
     dernières
    0.45
    зеро
    0.44
     further
    0.43
    here
    0.42
    recently
    0.42
    gover
    0.42
    Activations Density 0.015%

    No Known Activations