© 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. 1-CLT-HP
    7. 15946
    Prev
    Next
    INDEX
    Explanations

    ostok

    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
    ostok
    -1.25
     Califor
    -0.60
    кобрита
    -0.57
    бурга
    -0.54
     Tob
    -0.53
     conf
    -0.53
    hetti
    -0.52
     Albu
    -0.52
     Teng
    -0.51
    Errorf
    -0.50
    POSITIVE LOGITS
     resourceCulture
    0.63
     strijd
    0.56
     natten
    0.56
    rungsseite
    0.55
    nians
    0.54
     médicas
    0.50
     téléph
    0.50
     laborales
    0.49
     femininas
    0.48
     religieuses
    0.48
    Activations Density 0.012%

    No Known Activations