© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 15229
    Prev
    Next
    INDEX
    Explanations

    -omics studies (fields)

    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
    getMenuInflater
    -0.84
    IsContent
    -0.73
    BindView
    -0.69
    complexContent
    -0.67
    IBOutlet
    -0.66
    
    -0.65
     ComVisible
    -0.65
     InputDecoration
    -0.64
    aneo
    -0.64
    SerializeField
    -0.61
    POSITIVE LOGITS
    PhysRev
    0.56
    __':
    0.48
    RTLE
    0.46
    thaw
    0.45
    TH
    0.44
     arresting
    0.44
    <bos>
    0.44
    sa
    0.44
    Criminal
    0.42
     Railroads
    0.42
    Activations Density 0.051%

    No Known Activations