© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 9177
    Prev
    Next
    INDEX
    Explanations

    code related

    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
    SourceChecksum
    -0.90
     ISNI
    -0.76
     CreateTagHelper
    -0.72
    EndContext
    -0.67
     >=",
    -0.66
    Atsauces
    -0.64
     pymongo
    -0.62
     <>",
    -0.60
    Carcinogenicity
    -0.58
    TemporalType
    -0.58
    POSITIVE LOGITS
     صوتيه
    0.67
     recta
    0.45
    seu
    0.44
    Flop
    0.44
    rophe
    0.44
    outState
    0.43
     başına
    0.42
    Franco
    0.41
    Direct
    0.41
    IndentedString
    0.41
    Activations Density 3.750%

    No Known Activations