© 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. 0-CLT-HP
    7. 45532
    Prev
    Next
    INDEX
    Explanations

    icom

    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
    ########.
    -0.83
    icom
    -0.76
    acti
    -0.71
    NS
    -0.69
     acti
    -0.65
    期刊论文
    -0.64
    EndInit
    -0.60
    icha
    -0.60
    ulman
    -0.60
    Datuak
    -0.59
    POSITIVE LOGITS
    Conclusie
    0.60
    sidemargin
    0.53
    addPreferredGap
    0.52
     condado
    0.51
     disposent
    0.50
     specialise
    0.50
    řevě
    0.50
     VizieR
    0.49
    complexContent
    0.49
    "]);
    0.49
    Activations Density 0.126%

    No Known Activations