© 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
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 3081
    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
    исленность
    -0.67
    '
    -0.55
    ,
    -0.55
     further
    -0.54
     thus
    -0.51
     equals
    -0.48
     therefore
    -0.48
     equal
    -0.48
     AssemblyCulture
    -0.47
    DrawerLayout
    -0.46
    POSITIVE LOGITS
     autorytatywna
    0.67
     betweenstory
    0.60
    wiſe
    0.57
     Efq
    0.56
    󠁴
    0.55
     étoient
    0.54
    ]=>
    0.53
    WSGI
    0.53
    加坡
    0.52
     AssemblyTitle
    0.51
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.