© 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. 3166
    Prev
    Next
    INDEX
    Explanations

    breathing, air

    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
    fromnode
    -0.55
    DllImport
    -0.54
    marginVertical
    -0.47
    escar
    -0.46
     carlo
    -0.46
     elástica
    -0.45
    حوالہ
    -0.45
    DIPSETTING
    -0.44
    Sucesor
    -0.44
    SystemColors
    -0.44
    POSITIVE LOGITS
     mergeFrom
    0.71
    Portail
    0.64
     linkovi
    0.62
    rrggbb
    0.60
    msgTypes
    0.57
    DropTable
    0.56
    reich
    0.56
    elemField
    0.54
    DockStyle
    0.53
    EditorBrowsable
    0.53
    Activations Density 0.005%

    No Known Activations