© 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. 0-CLT-HP
    7. 92098
    Prev
    Next
    INDEX
    Explanations

    dissolve

    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
     limited
    -1.10
     dissolve
    -0.94
    limited
    -0.84
     dissolved
    -0.83
     dissolving
    -0.82
     dissolution
    -0.78
     dissolves
    -0.75
     limitada
    -0.72
    diss
    -0.71
     limitée
    -0.71
    POSITIVE LOGITS
    MigrationBuilder
    0.76
    JspWriter
    0.72
    WithMany
    0.68
     Amish
    0.65
     NgModule
    0.63
     onus
    0.63
     ProtoMessage
    0.61
    photobucket
    0.60
     Wikiped
    0.59
    cyd
    0.59
    Activations Density 0.046%

    No Known Activations