© 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
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 90824
    Prev
    Next
    INDEX
    Explanations

    anything

    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
     everything
    -1.53
     anything
    -1.45
    everything
    -1.25
     Everything
    -1.22
    Everything
    -1.18
     Anything
    -1.16
    Anything
    -1.13
    anything
    -1.09
     EVERYTHING
    -1.06
     whatever
    -0.96
    POSITIVE LOGITS
     else
    0.81
    ItemBackground
    0.66
    entrion
    0.55
    else
    0.55
    clusal
    0.54
     Bioaccumulative
    0.53
     loài
    0.52
    astéro
    0.50
    بالإنجليزية
    0.48
     conta
    0.48
    Activations Density 0.052%

    No Known Activations