© 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. 15957
    Prev
    Next
    INDEX
    Explanations

    chemistry

    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
    Geplaatst
    -0.66
     hendes
    -0.61
    ResumeLayout
    -0.61
    tonode
    -0.60
     MyBatis
    -0.57
     OMITBAD
    -0.56
    weder
    -0.56
     betweenstory
    -0.55
    principalTable
    -0.54
     hennes
    -0.54
    POSITIVE LOGITS
    ball
    0.67
    s
    0.60
    nasium
    0.56
    ConstraintMaker
    0.53
    becue
    0.52
     Ball
    0.51
    fall
    0.50
     farina
    0.50
    RLock
    0.48
    Ball
    0.47
    Activations Density 0.022%

    No Known Activations