© 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. 43453
    Prev
    Next
    INDEX
    Explanations

    spilling

    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
     spilling
    -0.72
     tonic
    -0.65
     dripping
    -0.64
     sublimation
    -0.63
     launching
    -0.62
     drafts
    -0.61
     whipping
    -0.61
     Launching
    -0.61
    ostante
    -0.59
     abstinence
    -0.58
    POSITIVE LOGITS
    Personendaten
    0.60
    protoimpl
    0.60
    Jeografia
    0.59
    a
    0.56
    RenderAtEndOf
    0.54
    iastes
    0.52
    e
    0.52
    addPreferredGap
    0.51
    enet
    0.50
    terase
    0.50
    Activations Density 0.226%

    No Known Activations