© 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. 42546
    Prev
    Next
    INDEX
    Explanations

    technical content

    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
    ings
    -1.72
    ds
    -1.32
    INGS
    -1.21
    ls
    -1.05
    als
    -0.98
    ils
    -0.90
    ments
    -0.85
     ds
    -0.85
    DS
    -0.85
    nings
    -0.76
    POSITIVE LOGITS
     thérape
    0.81
     Cæsar
    0.80
     imprimée
    0.78
     extérieurs
    0.77
     himſelf
    0.76
     chré
    0.76
     nemlig
    0.76
     étoient
    0.73
     themſelves
    0.69
     kjent
    0.69
    Activations Density 0.040%

    No Known Activations