Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 22-CLT-HP
    4. 74365
    Prev
    Next
    INDEX
    Explanations

    j

    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
    ousand
    -0.75
    naphthal
    -0.74
    ]--;
    -0.74
    ngthen
    -0.71
    tahankan
    -0.71
    oient
    -0.70
    NESDAY
    -0.70
    \<^
    -0.69
    IFORNIA
    -0.69
    troppo
    -0.69
    POSITIVE LOGITS
    k
    0.58
    se
    0.56
    mar
    0.54
    K
    0.51
    R
    0.51
    St
    0.51
    el
    0.51
    pro
    0.50
    bar
    0.50
    le
    0.50
    Activations Density 0.051%

    No Known Activations