© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 43318
    Prev
    Next
    INDEX
    Explanations

    away and travel

    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
    AWAY
    -1.14
     enfans
    -1.10
     Away
    -1.09
     purpoſe
    -1.09
     avoient
    -1.07
     feroit
    -1.02
     mauva
    -1.01
     plufieurs
    -0.99
    Away
    -0.98
     Eſ
    -0.98
    POSITIVE LOGITS
    ,
    0.57
     des
    0.56
     in
    0.54
      
    0.54
     for
    0.53
     from
    0.53
    ↵
    0.50
     (
    0.47
     e
    0.47
     From
    0.47
    Activations Density 1.598%

    No Known Activations