© 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. 0-CLT-HP
    4. 1913
    Prev
    Next
    INDEX
    Explanations

    lifer

    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
     normes
    -0.59
    GrantedAuthority
    -0.58
     Boron
    -0.57
     Handles
    -0.55
     lugs
    -0.54
     sociala
    -0.54
     labours
    -0.53
    pendente
    -0.53
     himo
    -0.53
     Motive
    -0.53
    POSITIVE LOGITS
    bed
    0.65
    room
    0.64
    ged
    0.60
    sters
    0.58
    nin
    0.57
    ed
    0.57
    Gemeinden
    0.56
    ers
    0.54
    ary
    0.54
    pets
    0.54
    Activations Density 0.045%

    No Known Activations