© 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. 5-CLT-HP
    7. 4629
    Prev
    Next
    INDEX
    Explanations

    components

    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
     HasFactory
    -0.69
     esternos
    -0.60
    jsonwebtoken
    -0.55
     itſelf
    -0.55
    ixante
    -0.55
     Corsica
    -0.54
     houſe
    -0.54
     derni
    -0.54
     Tami
    -0.53
     несу
    -0.53
    POSITIVE LOGITS
    :
    0.66
     utafitiHapana
    0.51
    Datuak
    0.47
    ag
    0.46
    called
    0.46
    no
    0.45
     called
    0.45
     :
    0.45
    out
    0.44
     plus
    0.44
    Activations Density 0.006%

    No Known Activations