© 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. 92797
    Prev
    Next
    INDEX
    Explanations

    searching data

    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
    <bos>
    -0.52
    =""/>
    -0.49
     Winaray
    -0.49
     intorno
    -0.48
     \&
    -0.48
    ┓
    -0.48
     Приступљено
    -0.47
    Clik
    -0.47
     amikor
    -0.46
    jetos
    -0.45
    POSITIVE LOGITS
    principalTable
    0.65
     للاسماء
    0.61
     estekak
    0.60
    Portale
    0.58
     not
    0.54
     checksum
    0.53
    Controllo
    0.53
    studies
    0.52
     esterni
    0.51
    isseurs
    0.51
    Activations Density 0.001%

    No Known Activations