© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 38969
    Prev
    Next
    INDEX
    Explanations

    particular

    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
    cordova
    -0.64
    ########.
    -0.63
     enkelte
    -0.51
     continúas
    -0.50
    ticamente
    -0.48
     procurando
    -0.47
    #+#
    -0.47
    rientes
    -0.46
    FS
    -0.44
     derniers
    -0.44
    POSITIVE LOGITS
     raiſ
    0.79
     seiz
    0.76
    audiovisuel
    0.73
     myſelf
    0.71
     themſelves
    0.70
    ergies
    0.68
     uſed
    0.68
     uſe
    0.68
     reaſon
    0.66
     itſelf
    0.65
    Activations Density 0.087%

    No Known Activations