© 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. 4-CLT-HP
    7. 3139
    Prev
    Next
    INDEX
    Explanations

    positive affirmations

    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
     triliun
    -0.53
     faſt
    -0.51
     ModelRenderer
    -0.50
     uſed
    -0.50
    "]);
    -0.49
    katapos
    -0.49
    Bibliograf
    -0.48
     ſta
    -0.48
    erta
    -0.48
     themſelves
    -0.47
    POSITIVE LOGITS
     or
    0.75
    ,
    0.73
    none
    0.71
    instead
    0.71
     instead
    0.66
    any
    0.63
     вместо
    0.63
    .
    0.63
    Instead
    0.59
    ValueGeneration
    0.57
    Activations Density 0.004%

    No Known Activations