© 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. 5-CLT-HP
    4. 802
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     precisely
    -0.52
    клопе
    -0.52
    Geplaatst
    -0.50
    határoz
    -0.49
    #+#
    -0.49
     GenerationType
    -0.49
    SharedDtor
    -0.48
     defined
    -0.47
     exactly
    -0.47
    İstinadlar
    -0.47
    POSITIVE LOGITS
    ękuję
    0.59
    principalTable
    0.57
    iastes
    0.56
     Null
    0.54
    Activité
    0.53
     Abdu
    0.53
    aville
    0.52
    łaj
    0.52
    aktery
    0.52
     Barrier
    0.52
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.