© 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. 0-CLT-HP
    7. 42050
    Prev
    Next
    INDEX
    Explanations

    subjected

    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
     cases
    -0.91
    cases
    -0.85
     Cases
    -0.78
    Cases
    -0.74
     CASES
    -0.65
     Fälle
    -0.64
     Reſ
    -0.62
     Efq
    -0.59
     ſche
    -0.59
     atve
    -0.59
    POSITIVE LOGITS
    igshid
    0.68
    ness
    0.58
    getNome
    0.54
    GEBURTSDATUM
    0.54
    ρούν
    0.53
     läs
    0.53
    atisfaction
    0.52
    ámenes
    0.52
    makeConstraints
    0.51
    ineno
    0.51
    Activations Density 0.251%

    No Known Activations