© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 1053
    Prev
    Next
    INDEX
    Explanations

    1

    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
    ffindor
    -0.57
    1
    -0.57
    1
    -0.51
     ১
    -0.43
     thirteen
    -0.42
     sixteen
    -0.41
     fifteen
    -0.40
     १
    -0.38
    ing
    -0.37
    zehn
    -0.37
    POSITIVE LOGITS
    \{\\
    1.01
    st
    0.89
    ,
    0.73
     يتيمه
    0.73
     nakalista
    0.72
    存于互联网档案馆
    0.71
    abestanden
    0.70
    9
    0.69
    +#+#
    0.68
    .
    0.67
    Activations Density 0.899%

    No Known Activations