© 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. 2835
    Prev
    Next
    INDEX
    Explanations

    chromatography

    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
    utenants
    -0.84
     tartalomajánló
    -0.77
     MotionEvent
    -0.67
    extAlignment
    -0.66
    sidemargin
    -0.66
    sizeCache
    -0.64
     geométrico
    -0.62
     wireType
    -0.60
     lie
    -0.58
     manières
    -0.58
    POSITIVE LOGITS
    oraz
    0.47
     total
    0.45
    phylococcus
    0.45
     filma
    0.44
    sh
    0.44
     cho
    0.44
    sela
    0.44
    odos
    0.44
     the
    0.44
     gain
    0.43
    Activations Density 0.001%

    No Known Activations