© 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. 3841
    Prev
    Next
    INDEX
    Explanations

    and

    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
    Autoritní
    -0.77
     FetchType
    -0.71
    帖最后由
    -0.66
    WithIOException
    -0.65
     dignité
    -0.63
    balleur
    -0.61
    OGND
    -0.60
     législation
    -0.58
    цезда
    -0.57
     fieldNum
    -0.57
    POSITIVE LOGITS
     source
    0.73
     basis
    0.67
     as
    0.66
     means
    0.65
     way
    0.61
     indicator
    0.61
     cornerstone
    0.59
     reminder
    0.59
     for
    0.56
     part
    0.56
    Activations Density 0.002%

    No Known Activations