© 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. 4-CLT-HP
    7. 3124
    Prev
    Next
    INDEX
    Explanations

    than

    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
    DockStyle
    -0.81
     tartalomajánló
    -0.71
     contextLoads
    -0.67
    <bos>
    -0.65
    brainly
    -0.65
     Reverso
    -0.63
    Nuorodos
    -0.63
    BagConstraints
    -0.62
    writeField
    -0.61
     Italijani
    -0.61
    POSITIVE LOGITS
     are
    0.57
     to
    0.53
     apply
    0.47
     come
    0.46
     is
    0.45
    to
    0.44
     exist
    0.44
     providing
    0.42
     you
    0.41
    ppio
    0.41
    Activations Density 0.007%

    No Known Activations