© 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. 0-CLT-HP
    7. 92411
    Prev
    Next
    INDEX
    Explanations

    cleft

    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
     cleft
    -0.96
     betweenstory
    -0.89
    itoria
    -0.84
     متعلقه
    -0.83
    rungsseite
    -0.79
     pauvres
    -0.77
    Geplaatst
    -0.75
     avoient
    -0.73
    tagext
    -0.72
     automatiques
    -0.69
    POSITIVE LOGITS
     towards
    0.52
     Frick
    0.52
    cif
    0.51
    文書
    0.50
     deal
    0.48
     blowing
    0.48
     Fri
    0.47
     referencing
    0.47
     sen
    0.47
    pol
    0.47
    Activations Density 0.086%

    No Known Activations