© 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. 0-CLT-HP
    7. 43653
    Prev
    Next
    INDEX
    Explanations

    8

    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
     resourceCulture
    -1.18
     MainAxisSize
    -1.11
     defaultstate
    -1.08
     Chwiliwch
    -1.05
     beginnetje
    -1.05
     nahilalakip
    -1.05
    tvguidetime
    -0.99
     utafitiHapana
    -0.99
    InjectAttribute
    -0.98
     disambiguazione
    -0.97
    POSITIVE LOGITS
    9
    1.08
    2
    1.05
    3
    1.02
    5
    0.99
    8
    0.99
    6
    0.98
    4
    0.97
    1
    0.94
    7
    0.92
    0
    0.85
    Activations Density 0.069%

    No Known Activations