© 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. 1-CLT-HP
    4. 45578
    Prev
    Next
    INDEX
    Explanations

    conservation

    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
    expandindo
    -1.04
    EndProject
    -0.90
    SequentialGroup
    -0.84
    IsContent
    -0.83
    DotNetBar
    -0.82
     صوتيه
    -0.81
    uxxxx
    -0.81
    StandardCharsets
    -0.79
    OGND
    -0.79
     AssemblyCulture
    -0.79
    POSITIVE LOGITS
    sy
    0.45
     more
    0.43
     on
    0.38
    s
    0.37
     sy
    0.36
    ind
    0.36
     drop
    0.35
    ัก
    0.34
    ereo
    0.34
    ya
    0.33
    Activations Density 0.010%

    No Known Activations