© 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. 20-CLT-HP
    7. 75913
    Prev
    Next
    INDEX
    Explanations

    Varied 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
    was
    -0.93
     was
    -0.75
    wasn
    -0.71
     était
    -0.68
    Was
    -0.68
    were
    -0.68
    était
    -0.68
     была
    -0.65
    étaient
    -0.65
     wasn
    -0.64
    POSITIVE LOGITS
     is
    0.59
     changes
    0.58
     slips
    0.56
    WithIOException
    0.56
     could
    0.53
     ranges
    0.52
     onCancelled
    0.52
     borders
    0.50
    UnknownFieldSet
    0.48
     IS
    0.48
    Activations Density 0.001%

    No Known Activations