© 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. 20-CLT-HP
    7. 75714
    Prev
    Next
    INDEX
    Explanations

    Various text snippets

    np_max-act-logits · 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
     <<<<<<<<<<<<<<
    -0.72
    balleur
    -0.66
     تانيه
    -0.66
     Asia
    -0.65
    enumi
    -0.63
     Asie
    -0.62
     насељу
    -0.61
    Obrázky
    -0.60
    UrlResolution
    -0.58
     Asante
    -0.57
    POSITIVE LOGITS
    OF
    0.46
     O
    0.46
     MOL
    0.43
    ❋
    0.43
     Prop
    0.43
    protoc
    0.43
    O
    0.42
     bero
    0.41
     kasarigan
    0.41
     plurality
    0.40
    Activations Density 0.003%

    No Known Activations