© 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. 20-CLT-HP
    7. 75008
    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
    target
    -0.78
     cible
    -0.73
    Target
    -0.72
     target
    -0.70
     Target
    -0.69
     Targets
    -0.68
    TARGET
    -0.66
     Targeted
    -0.64
    MigrationBuilder
    -0.64
     TARGET
    -0.59
    POSITIVE LOGITS
     ready
    0.58
     principal
    0.52
    ниципа
    0.49
     unexpected
    0.48
     Ready
    0.47
    ManagedBean
    0.47
    rateful
    0.47
    posedge
    0.46
     unwilling
    0.46
    MLLoader
    0.44
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.