© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 46155
    Prev
    Next
    INDEX
    Explanations

    develop

    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
     CreateTagHelper
    -0.90
     defaultstate
    -0.87
    Становништво
    -0.85
    AddTagHelper
    -0.85
     kasarigan
    -0.80
     MainAxisSize
    -0.78
     referenties
    -0.77
     tartalomajánló
    -0.77
    principalTable
    -0.75
     RouterModule
    -0.75
    POSITIVE LOGITS
     for
    0.58
     on
    0.57
     by
    0.51
     with
    0.49
     the
    0.49
     and
    0.49
     from
    0.49
     your
    0.49
     in
    0.48
     all
    0.47
    Activations Density 0.004%

    No Known Activations