© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 91068
    Prev
    Next
    INDEX
    Explanations

    initialization

    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
    Negative Logits
     settled
    -0.44
    JsonIgnore
    -0.43
    googleapis
    -0.41
     rost
    -0.39
    よい
    -0.39
    transQ
    -0.38
     closely
    -0.38
    基
    -0.38
    ある
    -0.38
    AsUp
    -0.38
    POSITIVE LOGITS
     stället
    0.84
     eventdata
    0.79
    ftagPool
    0.71
    NUMX
    0.70
    FunctionFlags
    0.68
     blessés
    0.67
    ########.
    0.66
     automatiques
    0.66
    \{\\
    0.65
     unknownFields
    0.65
    Activations Density 0.048%

    No Known Activations