© 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. 5-CLT-HP
    7. 94516
    Prev
    Next
    INDEX
    Explanations

    ready to

    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
    .
    -0.52
     Bioaccumulative
    -0.50
     volna
    -0.50
     semplicemente
    -0.49
    EDEFAULT
    -0.46
     pés
    -0.45
    zipped
    -0.44
    ájá
    -0.44
    PEND
    -0.44
     strå
    -0.43
    POSITIVE LOGITS
    Cyfeiriadau
    0.74
    InjectAttribute
    0.66
     onPostExecute
    0.63
    ErrUnexpectedEOF
    0.62
     commit
    0.61
    uxxxx
    0.61
    ConstraintMaker
    0.60
    ValueStyle
    0.59
    ViewImports
    0.59
    withIdentifier
    0.58
    Activations Density 0.001%

    No Known Activations