© 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. 94082
    Prev
    Next
    INDEX
    Explanations

    purpose

    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
    :
    -0.47
     not
    -0.46
    ódó
    -0.46
    NSIndexPath
    -0.45
    .
    -0.40
     consultato
    -0.40
     in
    -0.39
     zd
    -0.38
     bu
    -0.37
     akun
    -0.37
    POSITIVE LOGITS
    SourceChecksum
    1.09
    ftagPool
    0.91
     Roskov
    0.90
    oredCriteria
    0.84
    Autoritní
    0.80
    LookAnd
    0.78
     HasFactory
    0.77
    
    0.77
     myſelf
    0.75
    Abit
    0.75
    Activations Density 0.003%

    No Known Activations