© 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. 72791
    Prev
    Next
    INDEX
    Explanations

    Technical data

    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
    enumi
    -0.58
    findpost
    -0.56
     useAppContext
    -0.56
    tvguidetime
    -0.54
    hoeddwyd
    -0.53
    +#+#
    -0.52
    +#+
    -0.52
    UMBIA
    -0.50
    ="{{$
    -0.50
    فایل‌لار
    -0.49
    POSITIVE LOGITS
     to
    1.14
    to
    0.65
     antaranya
    0.57
     raise
    0.55
    wpi
    0.54
     didst
    0.53
    NOUN
    0.52
    piram
    0.52
     hereto
    0.51
     classify
    0.51
    Activations Density 0.019%

    No Known Activations