© 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. 15969
    Prev
    Next
    INDEX
    Explanations

    accessible

    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
     accessible
    -0.66
     accessibility
    -0.58
     acces
    -0.57
     ComVisible
    -0.53
    REAM
    -0.51
     access
    -0.50
    accessible
    -0.50
     Acces
    -0.50
     Accessible
    -0.49
     Erbe
    -0.49
    POSITIVE LOGITS
     complètes
    0.84
     propOrder
    0.74
    tagHelperRunner
    0.69
     supérieurs
    0.68
     automatiques
    0.68
    LLocation
    0.66
    enumi
    0.65
     remplacé
    0.64
     intérieur
    0.63
     utafitiHapana
    0.63
    Activations Density 0.066%

    No Known Activations