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. 74226
    Prev
    Next
    INDEX
    Explanations

    Programming/software context

    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
     EPR
    -0.59
     '\\;'
    -0.59
    saf
    -0.55
     pellet
    -0.54
    errHandler
    -0.54
    ượu
    -0.54
     Pharisees
    -0.53
    ForValue
    -0.53
    InitVars
    -0.53
     Италијани
    -0.51
    POSITIVE LOGITS
    AnchorStyles
    0.73
    Activités
    0.51
    ---*/
    0.51
    }`}>
    0.49
    MLLoader
    0.47
    ConstraintMaker
    0.47
    发表于
    0.47
    RenderAtEndOf
    0.46
     hindurch
    0.46
    zied
    0.46
    Activations Density 0.009%

    No Known Activations