© 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. 1-CLT-HP
    7. 45995
    Prev
    Next
    INDEX
    Explanations

    mor

    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
     loue
    -0.57
     uſed
    -0.57
     pleaſure
    -0.57
    IonicModule
    -0.55
     ſp
    -0.55
     poffe
    -0.55
     againſt
    -0.54
     tori
    -0.54
     ſhe
    -0.53
     proofs
    -0.53
    POSITIVE LOGITS
    первых
    0.57
    GOTREF
    0.52
    igshid
    0.49
    IMPORTED
    0.48
    iram
    0.46
    ГЛА
    0.46
    findpost
    0.45
    UIControlState
    0.45
     GenerationType
    0.45
    edoc
    0.44
    Activations Density 0.003%

    No Known Activations