© 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. 91191
    Prev
    Next
    INDEX
    Explanations

    health, injuries, treatment

    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
     was
    -0.52
     stood
    -0.51
     banged
    -0.50
    was
    -0.49
    ώς
    -0.48
    aremos
    -0.47
     quenched
    -0.47
    "]);
    -0.47
    ?>"
    -0.47
     Vor
    -0.46
    POSITIVE LOGITS
    halb
    0.65
     OFDb
    0.65
    bootstrapcdn
    0.60
     occaf
    0.59
     strikes
    0.59
     Efq
    0.58
    DockStyle
    0.57
    estro
    0.56
    LookAnd
    0.54
     Affects
    0.53
    Activations Density 0.006%

    No Known Activations