© 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. 5-CLT-HP
    7. 4963
    Prev
    Next
    INDEX
    Explanations

    return

    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
    ftagPool
    -0.55
    packs
    -0.49
    Playback
    -0.48
    igel
    -0.47
     Tak
    -0.47
     jadx
    -0.46
    ển
    -0.46
    chette
    -0.45
    ContextHolder
    -0.45
    ksha
    -0.45
    POSITIVE LOGITS
     OFDb
    0.69
     Monfieur
    0.63
     ſtate
    0.63
     itſelf
    0.61
    ⁩
    0.58
    Affiliation
    0.57
     myſelf
    0.56
     purpoſe
    0.56
     statistics
    0.55
     quæ
    0.54
    Activations Density 0.000%

    No Known Activations