© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 40089
    Prev
    Next
    INDEX
    Explanations

    lyric

    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
     song
    -1.41
    song
    -1.26
     Song
    -1.24
     SONG
    -1.23
     Singing
    -1.22
    Song
    -1.17
     singing
    -1.15
     sing
    -1.11
    Singing
    -1.11
     sings
    -1.09
    POSITIVE LOGITS
    box
    0.47
    doms
    0.47
    getHours
    0.46
    dom
    0.45
     obrigado
    0.45
    AsUp
    0.45
    dhist
    0.44
    Wright
    0.43
    mentazione
    0.43
    lesse
    0.42
    Activations Density 0.156%

    No Known Activations