© 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. 4517
    Prev
    Next
    INDEX
    Explanations

    slaves

    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
    modelBuilder
    -0.51
    ɵɵ
    -0.48
    kari
    -0.45
     Signalez
    -0.45
    洋
    -0.44
     Mede
    -0.43
     seme
    -0.42
    tease
    -0.42
    THY
    -0.41
     Seen
    -0.40
    POSITIVE LOGITS
    databind
    0.67
    ########.
    0.66
    RepeatedField
    0.63
     considérons
    0.61
    Demografie
    0.60
     出版
    0.60
    Παραπομπές
    0.59
     pylint
    0.58
    __':
    0.57
     fata
    0.56
    Activations Density 0.000%

    No Known Activations