© 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. 45631
    Prev
    Next
    INDEX
    Explanations

    encoding

    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
    <bos>
    -0.69
    UMBIA
    -0.50
    AKI
    -0.42
    pherals
    -0.41
    ola
    -0.40
    никами
    -0.39
    ToListAsync
    -0.38
    deaux
    -0.38
     McMahon
    -0.38
    calciatore
    -0.38
    POSITIVE LOGITS
    ValueStyle
    0.82
    LookAnd
    0.81
     متعلقه
    0.79
     pinulongan
    0.75
     CreateTagHelper
    0.74
    ыгана
    0.72
     صوتيه
    0.70
     nakalista
    0.69
    #+#
    0.67
    ItemBackground
    0.67
    Activations Density 0.079%

    No Known Activations