© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 77578
    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
     autorytatywna
    -0.75
     twar
    -0.51
    UTRAL
    -0.50
     AssemblyTitle
    -0.49
    ropy
    -0.48
    rungsseite
    -0.47
    łaj
    -0.47
    Manbalar
    -0.46
    rican
    -0.46
     Sump
    -0.46
    POSITIVE LOGITS
    UIControlState
    0.63
    ReusableCell
    0.63
    PMailer
    0.52
     BorderRadius
    0.51
    Datuak
    0.50
    WireFormatLite
    0.50
    GEBURTSDATUM
    0.50
    EndInit
    0.49
    MessageOf
    0.49
    gridx
    0.49
    Activations Density 0.002%

    No Known Activations