© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 94200
    Prev
    Next
    INDEX
    Explanations

    recommendations, congrats, or code

    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
     recommend
    -1.45
     recommended
    -1.37
     Recommended
    -1.27
    recommended
    -1.21
    recommend
    -1.18
     recommends
    -1.16
     Recommend
    -1.15
    Recommended
    -1.12
     recommande
    -1.09
     RECOMMEND
    -1.09
    POSITIVE LOGITS
     Theſe
    0.74
    protoimpl
    0.73
    mtrl
    0.69
    MockMvc
    0.67
    SharedCtor
    0.66
     Elvira
    0.66
     torchvision
    0.65
     exploiting
    0.65
    afficheront
    0.63
     ſtre
    0.63
    Activations Density 0.208%

    No Known Activations