© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 93501
    Prev
    Next
    INDEX
    Explanations

    aner

    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
     becomes
    -0.64
     became
    -0.62
     quickly
    -0.60
    became
    -0.59
     become
    -0.59
     suddenly
    -0.59
     spontaneously
    -0.56
     again
    -0.55
     soon
    -0.54
     BECOME
    -0.52
    POSITIVE LOGITS
     tartalomajánló
    0.68
    oretical
    0.64
    IsMutable
    0.62
    +#+#
    0.60
     témoins
    0.60
    aarrggbb
    0.59
     aanwezig
    0.59
     bakom
    0.59
    сылкі
    0.58
     saites
    0.58
    Activations Density 0.006%

    No Known Activations