© 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. 2210
    Prev
    Next
    INDEX
    Explanations

    education

    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
    TagMode
    -0.67
    usitis
    -0.65
    igshid
    -0.64
     بيها
    -0.63
    tagHelperRunner
    -0.62
     <=",
    -0.62
     beginnetje
    -0.60
     semula
    -0.59
    +#+#
    -0.57
     Exacts
    -0.55
    POSITIVE LOGITS
     to
    0.60
     how
    0.56
    AppendLine
    0.49
     LC
    0.47
     good
    0.46
    LMA
    0.45
    Perché
    0.44
     LCM
    0.44
    Meik
    0.44
     material
    0.44
    Activations Density 0.001%

    No Known Activations