© 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. 6186
    Prev
    Next
    INDEX
    Explanations

    placed

    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
    Negative Logits
    ssos
    -0.56
    /**
    -0.56
     محفوظة
    -0.55
     to
    -0.55
    enderror
    -0.54
    paravant
    -0.53
    batore
    -0.50
    below
    -0.49
     dados
    -0.49
    eye
    -0.49
    POSITIVE LOGITS
     on
    0.72
     upon
    0.61
     UPON
    0.59
     protoimpl
    0.54
    PreferredItem
    0.53
     VizieR
    0.53
     Upon
    0.53
    +#+
    0.53
    JsonHelper
    0.52
    findpost
    0.50
    Activations Density 0.001%

    No Known Activations