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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 2402
    Prev
    Next
    INDEX
    Explanations

    one

    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
     kasarigan
    -0.49
    zegovina
    -0.47
    ”]
    -0.47
    mption
    -0.46
     []).
    -0.42
    derdag
    -0.42
     correctes
    -0.41
    URDAY
    -0.40
     names
    -0.40
     conditions
    -0.39
    POSITIVE LOGITS
     that
    1.20
     which
    0.87
    that
    0.79
     used
    0.75
     thats
    0.74
     whose
    0.73
     waarop
    0.73
    rungsseite
    0.66
     يتيمه
    0.66
     auxquelles
    0.65
    Activations Density 0.002%

    No Known Activations