© 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. 5-CLT-HP
    7. 2766
    Prev
    Next
    INDEX
    Explanations

    the

    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
    homonymie
    -0.54
    posedge
    -0.52
     Influence
    -0.51
     influence
    -0.49
    IntoConstraints
    -0.49
     impact
    -0.46
    OGND
    -0.44
     Lordships
    -0.44
    influence
    -0.43
     Comparable
    -0.42
    POSITIVE LOGITS
     part
    0.85
    part
    0.84
     lenker
    0.66
     osa
    0.63
    //
    0.61
     précie
    0.60
     Meksiku
    0.60
     chi̍t
    0.59
    ArrowToggle
    0.58
    Part
    0.58
    Activations Density 0.005%

    No Known Activations