© 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. 5-CLT-HP
    7. 2910
    Prev
    Next
    INDEX
    Explanations

    Liking or enjoyment

    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
     to
    -0.53
     ſuch
    -0.47
    gemeen
    -0.43
     eating
    -0.43
    eats
    -0.42
     Dowling
    -0.42
    イナ
    -0.40
     utafitiHapana
    -0.40
    ียด
    -0.40
     Incoming
    -0.39
    POSITIVE LOGITS
     esternos
    0.75
    __*/
    0.73
    MemoryWarning
    0.72
    ɵɵ
    0.69
    AndEndTag
    0.68
    bouncycastle
    0.66
    +#+#
    0.65
     ComVisible
    0.63
    Witam
    0.63
     ModelRenderer
    0.62
    Activations Density 0.000%

    No Known Activations