© 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. 91185
    Prev
    Next
    INDEX
    Explanations

    Code snippets and quotations

    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
    возь
    -0.54
    டி
    -0.46
    })*/
    -0.46
     Nop
    -0.45
     éter
    -0.45
     referrerpolicy
    -0.45
     EMR
    -0.44
    에도
    -0.44
     ACR
    -0.43
    älter
    -0.43
    POSITIVE LOGITS
    XmlAccessorType
    0.70
    TargetException
    0.69
    بوابة
    0.68
    Ծանոթ
    0.68
    ########.
    0.67
    ViewFeatures
    0.67
    Geplaatst
    0.66
    ]='\
    0.63
    lgari
    0.63
    ContentAsync
    0.63
    Activations Density 0.000%

    No Known Activations