© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 93523
    Prev
    Next
    INDEX
    Explanations

    with

    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
     nakalista
    -0.61
     الفيلم
    -0.53
     capitales
    -0.53
    "]}
    -0.52
    UVWXYZ
    -0.52
    Referencie
    -0.52
    Fotó
    -0.51
    AccessorTable
    -0.50
    UNEP
    -0.50
     durata
    -0.50
    POSITIVE LOGITS
     swallows
    0.52
     ovulation
    0.52
    schild
    0.49
    Rüyada
    0.49
     flares
    0.48
    RTHOOK
    0.47
    FieldBuilder
    0.47
     passage
    0.47
    jakarta
    0.46
    thinkable
    0.46
    Activations Density 0.007%

    No Known Activations