© 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. 4-CLT-HP
    7. 1470
    Prev
    Next
    INDEX
    Explanations

    ban

    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
    rem
    -0.57
    tor
    -0.56
     externi
    -0.56
    קישורים
    -0.54
    st
    -0.53
     artigian
    -0.53
     metà
    -0.53
     uș
    -0.52
    ter
    -0.52
     HasFactory
    -0.50
    POSITIVE LOGITS
    cessed
    0.55
    Autoritní
    0.54
    ALAND
    0.53
    owna
    0.52
    isure
    0.51
    ayaquil
    0.50
    AXB
    0.50
    atecas
    0.50
    enegro
    0.49
    ailangan
    0.48
    Activations Density 0.000%

    No Known Activations