© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 10526
    Prev
    Next
    INDEX
    Explanations

    mammals

    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
     parcel
    -0.82
    IntoConstraints
    -0.79
     Parcel
    -0.68
    parcel
    -0.66
     BoxFit
    -0.64
    
    -0.62
    Parcel
    -0.60
     parcels
    -0.59
    illers
    -0.54
     knobs
    -0.53
    POSITIVE LOGITS
    BeginContext
    0.57
    ahnya
    0.53
    ecore
    0.52
    Autoritní
    0.51
     مُعرِّف
    0.48
    ly
    0.47
    Ź
    0.47
    كية
    0.46
    azon
    0.46
    feira
    0.45
    Activations Density 0.082%

    No Known Activations