© 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. 94905
    Prev
    Next
    INDEX
    Explanations

    possibility

    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
    Personensuche
    -0.48
    <bos>
    -0.46
    زال
    -0.44
     drapeau
    -0.43
     macchina
    -0.42
     mukaan
    -0.41
     précisément
    -0.40
     Unies
    -0.39
     öns
    -0.38
     mauvaise
    -0.38
    POSITIVE LOGITS
     betweenstory
    0.82
    setVerticalGroup
    0.73
    MessageOf
    0.69
     ويكيميديا
    0.67
    adpleegd
    0.66
    StoryboardSegue
    0.65
    rxjs
    0.63
    WriteBarrier
    0.62
    fromnode
    0.61
    '}>
    0.60
    Activations Density 0.010%

    No Known Activations