© 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. 39799
    Prev
    Next
    INDEX
    Explanations

    stro

    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
     senator
    -0.56
     собой
    -0.50
     Senator
    -0.49
     skimage
    -0.48
     granular
    -0.47
     stro
    -0.46
    kits
    -0.45
     strconv
    -0.45
    talk
    -0.45
    tte
    -0.44
    POSITIVE LOGITS
    
    0.81
     &___
    0.78
    RTEE
    0.75
    #+#
    0.73
    WriteBarrier
    0.68
    évaluateur
    0.68
    UserScript
    0.66
    WebControls
    0.65
     estekak
    0.62
     ujednoznacz
    0.61
    Activations Density 0.182%

    No Known Activations