© 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. 20-CLT-HP
    7. 73535
    Prev
    Next
    INDEX
    Explanations

    Universities

    np_max-act-logits · 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
     AssemblyProduct
    -0.49
    __;
    -0.49
     pousse
    -0.48
     punch
    -0.46
    lamic
    -0.44
    _));
    -0.44
    expandindo
    -0.44
    CGRectMake
    -0.44
     Lod
    -0.44
     ddelweddau
    -0.43
    POSITIVE LOGITS
     okuyayım
    0.63
    SharedDtor
    0.60
     szóci
    0.59
    verwijspagina
    0.57
     <<<<<<<<<<<<<<
    0.56
     Parcelable
    0.56
    tvguidetime
    0.54
    ंदीखरीदारी
    0.53
     Efq
    0.53
     "..\..\
    0.53
    Activations Density 0.001%

    No Known Activations