© 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. 1-CLT-HP
    7. 420
    Prev
    Next
    INDEX
    Explanations

    ha

    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
    ha
    -0.83
    ConstraintMaker
    -0.60
    ReusableCell
    -0.55
    HA
    -0.52
     breathed
    -0.49
    na
    -0.49
    n
    -0.49
    sou
    -0.46
     ha
    -0.46
    arsis
    -0.44
    POSITIVE LOGITS
     betweenstory
    0.75
     TestBed
    0.60
    ]--;
    0.56
    WSGI
    0.56
     České
    0.55
    oa̍t
    0.54
    ValueStyle
    0.54
    mêmes
    0.53
     kautta
    0.52
    writeFieldEnd
    0.52
    Activations Density 0.020%

    No Known Activations