© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 76942
    Prev
    Next
    INDEX
    Explanations

    dose

    np_max-act-logits · 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
    tanooga
    -0.51
    olar
    -0.49
     primary
    -0.49
    zin
    -0.49
     مرئيه
    -0.48
     Primary
    -0.47
    
    -0.47
    AMI
    -0.47
    bolista
    -0.46
    getItemId
    -0.46
    POSITIVE LOGITS
    Geplaatst
    0.66
    енча
    0.63
     beginnetje
    0.61
    Autoritní
    0.61
    ineno
    0.60
    SBATCH
    0.58
     '\\;'
    0.55
     hiér
    0.52
     Normdatei
    0.51
     surla
    0.50
    Activations Density 0.004%

    No Known Activations