© 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. 2502
    Prev
    Next
    INDEX
    Explanations

    Main

    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
    <?
    -0.68
     EconPapers
    -0.65
    gone
    -0.62
    tifies
    -0.59
    pless
    -0.58
    qvarna
    -0.58
    ])):
    -0.56
     him
    -0.55
     HasFactory
    -0.55
    givers
    -0.54
    POSITIVE LOGITS
    ,
    1.05
     we
    0.84
     they
    0.73
     in
    0.69
     for
    0.66
     оно
    0.65
     it
    0.58
     of
    0.58
     although
    0.58
     from
    0.55
    Activations Density 0.000%

    No Known Activations