© 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
    2. Gemma-2-2B
    3. 4-CLT-HP
    4. 2592
    Prev
    Next
    INDEX
    Explanations

    code

    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
     notes
    -0.56
     Notes
    -0.55
     OFDb
    -0.54
    FORME
    -0.54
    lege
    -0.54
     Nowak
    -0.53
     comments
    -0.52
     Meaning
    -0.51
    הערות
    -0.50
    ys
    -0.50
    POSITIVE LOGITS
     propOrder
    0.69
    tvguidetime
    0.66
    verwijspagina
    0.65
    Gön
    0.63
    Personendaten
    0.59
    <bos>
    0.57
     kasarigan
    0.56
    <?
    0.56
    ScopeManager
    0.55
    TypedDataSet
    0.55
    Activations Density 0.004%

    No Known Activations