© 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. 40300
    Prev
    Next
    INDEX
    Explanations

    stable

    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
    Stable
    -1.68
     Stable
    -1.61
    stable
    -1.59
     stable
    -1.36
     stabilized
    -1.23
    stability
    -1.23
     stabilize
    -1.22
    Stab
    -1.20
    stabili
    -1.19
     Stab
    -1.16
    POSITIVE LOGITS
    ,
    0.59
     out
    0.59
     and
    0.55
     amp
    0.53
     nor
    0.49
     as
    0.47
     regional
    0.47
     (
    0.47
     in
    0.46
     re
    0.46
    Activations Density 1.686%

    No Known Activations