© 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. 222
    Prev
    Next
    INDEX
    Explanations

    The

    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
     disambiguazione
    -0.81
    MENAFN
    -0.81
     Administrativna
    -0.81
    Digitized
    -0.74
    ніципалі
    -0.73
    <bos>
    -0.72
     pageContext
    -0.69
     MessageBoxIcon
    -0.66
     autorytatywna
    -0.65
    Scénario
    -0.65
    POSITIVE LOGITS
    ,
    0.49
    .
    0.45
    load
    0.45
    RequestMethod
    0.44
    OwnProperty
    0.44
     comigo
    0.44
     $
    0.43
    ry
    0.41
    nocache
    0.40
    ;
    0.40
    Activations Density 0.010%

    No Known Activations