© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 16198
    Prev
    Next
    INDEX
    Explanations

    lic

    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
    Negative Logits
    seiti
    -0.54
     flèche
    -0.49
     Lightboxes
    -0.48
    haps
    -0.48
     Hob
    -0.47
     sosis
    -0.47
    dorm
    -0.47
    ocidad
    -0.47
    cshtml
    -0.46
     HOB
    -0.46
    POSITIVE LOGITS
    jgl
    0.63
    RUnlock
    0.59
    êtement
    0.54
    titleMargin
    0.53
    SerializedName
    0.53
     inspiradoras
    0.53
     onBind
    0.52
    Kaieteur
    0.51
     invokingState
    0.51
    ®:
    0.50
    Activations Density 0.034%

    No Known Activations