© 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. 92510
    Prev
    Next
    INDEX
    Explanations

    accessing

    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
     accessing
    -0.97
     accessed
    -0.86
    Accessing
    -0.84
    ftagPool
    -0.70
    telephone
    -0.65
    rungsseite
    -0.64
     مشين
    -0.64
    accéder
    -0.64
     accedere
    -0.63
     acceder
    -0.62
    POSITIVE LOGITS
    s
    0.68
     the
    0.47
     iprot
    0.47
     base
    0.46
    
    0.46
     owner
    0.46
     Owner
    0.44
    oplasts
    0.44
    ی
    0.44
     correctes
    0.44
    Activations Density 0.149%

    No Known Activations