© 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. 0-CLT-HP
    7. 43149
    Prev
    Next
    INDEX
    Explanations

    aid

    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
    providedIn
    -0.71
     Membrane
    -0.69
     Inflammation
    -0.67
     haunt
    -0.66
    Membrane
    -0.63
     inflammation
    -0.61
    TIER
    -0.61
    inflated
    -0.60
     continuant
    -0.58
     Hydrology
    -0.58
    POSITIVE LOGITS
    <bos>
    0.82
     estekak
    0.69
    rungsseite
    0.65
    opress
    0.52
     '\\;'
    0.52
    Obrázky
    0.49
    исленность
    0.49
    RegistryLite
    0.47
    EDEFAULT
    0.47
     esternos
    0.46
    Activations Density 0.096%

    No Known Activations