© 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. 0-CLT-HP
    7. 95497
    Prev
    Next
    INDEX
    Explanations

    declare

    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
     claim
    -1.64
    claim
    -1.55
     claimed
    -1.52
    claimed
    -1.43
     Claim
    -1.41
     claims
    -1.40
     claiming
    -1.38
     CLAIM
    -1.37
    claims
    -1.34
    Claim
    -1.30
    POSITIVE LOGITS
    SpringBootTest
    0.76
     initComponents
    0.69
    afficheront
    0.62
     themselves
    0.62
     ourselves
    0.62
    ✨:
    0.61
     виправивши
    0.61
    PerformLayout
    0.61
     yourselves
    0.59
    eseorang
    0.58
    Activations Density 0.042%

    No Known Activations