© 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. 91163
    Prev
    Next
    INDEX
    Explanations

    Bed

    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
    BASEPATH
    -0.50
     intptr
    -0.49
    Personensuche
    -0.48
    InjectAttribute
    -0.47
    Sucesor
    -0.46
     Durée
    -0.46
    enterOuterAlt
    -0.45
    HomeAsUpEnabled
    -0.44
    RegisterType
    -0.42
    skinned
    -0.42
    POSITIVE LOGITS
     BoxFit
    0.69
     collaboration
    0.55
     residency
    0.53
    sizeCache
    0.53
    tagHelper
    0.53
     syndrome
    0.52
     philosophy
    0.52
    |}{$
    0.51
     investigation
    0.50
    клопе
    0.50
    Activations Density 0.000%

    No Known Activations