© 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. 77823
    Prev
    Next
    INDEX
    Explanations

    Miscellaneous topics

    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
     aidant
    -0.50
     Letter
    -0.46
    licer
    -0.45
    бурге
    -0.45
    siębior
    -0.44
     Normdatei
    -0.43
    Letter
    -0.42
    grine
    -0.42
    SDL
    -0.42
    itinéraire
    -0.42
    POSITIVE LOGITS
    abestanden
    0.65
    ########.
    0.64
     تكبرها
    0.59
    andExpect
    0.56
    UIControlState
    0.55
     cérami
    0.54
    حياتها
    0.53
     CreateTagHelper
    0.53
     beginnetje
    0.52
     disambiguazione
    0.52
    Activations Density 0.007%

    No Known Activations