© 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. 76531
    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
    IsMutable
    -0.67
    Hentet
    -0.66
    Portail
    -0.60
    ApiModelProperty
    -0.59
    Datuak
    -0.59
    MethodManager
    -0.55
    Jegyzetek
    -0.54
    GEBURTS
    -0.53
    xase
    -0.52
    Poppins
    -0.52
    POSITIVE LOGITS
     Year
    0.67
     rang
    0.63
     margin
    0.61
    %;
    0.61
     tam
    0.56
     Looked
    0.55
     primary
    0.55
     Primary
    0.54
    transQ
    0.54
    Primary
    0.54
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.